Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
AI-Based Sentiment Analysis for User Feedback Triage” project is designed to automate the analysis and prioritization of user feedback using Artificial Intelligence and Natural Language Processing (NLP).
OmniClaims Adjuster es una plataforma multi-agente impulsada por Gemini 3.1 que automatiza la evaluación de seguros. Combina análisis multimodal de daños, verificación de pólizas y detección de fraude en tiempo real para el sector Insurtech.
Synapse AI is a multi-agent enterprise AI platform where autonomous HR, CTO, CFO, and CEO agents collaborate in real time to automate interviews, workflow analysis, and strategic decision-making using multimodal AI and scalable cloud architecture.
AI agent queries live Milan public data (air quality, traffic, trees, demographics), reasons across datasets, and packages findings into encrypted memory crystals with cryptographic selective disclosure.
DemoMaster generates a demo pitch video from a git repo in one click
Sentinel_OS is an autonomous enterprise intelligence system that detects risks, coordinates AI agents, and orchestrates real-time operational response.
The end-to-end AI content engine for real estate agents. 4RealEstate Flow runs four AI agents that plan viral content, produce listing videos, and optimize paid ads autonomously. Every agent, their own marketing team.
The Agent Governance OS for autonomous AI in regulated industries. 9-vendor adversarial ensemble + Z3 formal proof + RFC 3161 court-grade audit chain. DORA + EU AI Act Art. 14 ready. Open-source Apache-2.0. Live demo at apohara.dev/consilium.
Real-time voice AI agent for enterprise customer support. Speechmatics streams live transcriptions, Claude generates intelligent responses instantly. Deployed on Vultr. Speak — get answered. No typing, no wait, no friction.
MenuTaste is a Featherless-powered AI agent deployed on Vultr that helps food entrepreneurs analyze food and drink ideas for nutrition signals, risk, market fit, launch readiness, and exportable business reports.
A multi-agent AI system that takes any news article or topic, finds the original wire story, crawls 15 global outlets, scores how much each outlet's coverage drifted from original, and visualizes the mutation chain as an interactive D3 tree + 3D globe.
An autonomous AI strategic intelligence system that discovers competitors, monitors market signals, predicts strategic threats, and autonomously generates executive-grade business recommendations using collaborative AI agents.
Review invoices, govern agent payments, respond to X402 payment challenges, and keep an audit trail finance teams can trust.
Google GenAI SDK (Gemini 2.5) + OpenCV + Tesseract OCR based autonomous multi-modal agent framework for continuous live-screen system auditing, intelligent technical reasoning, and asynchronous enterprise workflow automation via email pipelines.
TeamPulse turns Google Meet transcripts into instant meeting intelligence. Powered by Gemini, it extracts decisions, tasks, risks, and owners automatically — so your team never loses track of a commitment again.
CamSort is an autonomous camera prioritization agent that uses Google Gemini to analyze security camera feeds and rank them by operational priority based on natural language instructions from the operator.
AuthAgent is an AI-powered document analysis system that deploys four specialist agents to audit denial letters, identify compliance gaps, and auto-generate approval responses across healthcare, visa, finance, and grant domains.
Multi-agent enterprise governance platform with live AI inference and sequential pipeline orchestration.
TALOS — Autonomous Multi-Agent Supply Chain Defense System. Detects vendor stream failures, runs a 4-agent AI pipeline (Scout → Analyst → Broker → Forge), and executes a full vendor failover in under 60 seconds with human-in-the-loop authorization.
Multi-agent investment analysis platform with LLM-driven orchestration. Three modes: ticker analysis, PDF+market cross-analysis, and AI dialogue. Specialized agents run in parallel — Fundamental, Quant, Peer, and CIO — deployed on Vultr.
Agent Testnet is an open-source sandboxed parallel internet for AI agents: a self-contained world of fake services where agents can browse, interact, and break things - phishing, prompt injections, destructive tool calls - without touching the real web.
MUDRAIS Weaver & Voice: Multimodal Agentic Onboarding for Semantic Matchmaking
A trust layer for enterprise AI agents that detects prompt injection, data leaks, policy violations, and unsafe actions, enforcing secure, auditable, and compliant AI workflows with human oversight and risk scoring.
DecisionGraph gives AI agents permanent enterprise memory. Documents become a knowledge graph. Every decision is stored, tracked, and learned from. Any agent plugs in via MCP in 5 minutes. The enterprise gets smarter with every interaction.
BriefAI eliminates manual document prep by generating polished enterprise briefs in seconds. Choose a brief type, fill in the context, and let Gemini AI produce a professional document instantly
An AI powered interactive puppet theater where users control expressive 3D characters using real time hand gestures and facial expressions to create cinematic live performances inside a dynamic virtual stage.
BidLens is an async AI workflow that reads RFPs and vendor replies, extracts requirements, flags gaps and risks, and generates scorecards plus reports for faster procurement decisions.
An autonomous AI trading agent built for the Kraken xStocks Challenge. It analyzes market signals, executes trades programmatically via Kraken CLI, and visualizes performance through real‑time dashboards, backtesting, and risk‑management automation.
Upload any strategic document. Five adversarial AI agents — CFO, Market, Legal, Competitor, Execution — simultaneously attack it and deliver a severity-scored vulnerability report in under 90 seconds. demo credentials giovanni@acme.com red-team
CouncilOS is a collaborative multi-agent reasoning platform where AI models engage in human-like discussions to critique, refine, and evolve code analysis in real time for more reliable and research-oriented reasoning workflows.
PANTEK, an AI Chief Risk Officer powered by a dual-LLM architecture. We eradicate operational blindness by moving enterprises from static dashboards to a predictive digital twin that simulates cascading supply chain failures before they happen.
An autonomous multi-agent contract auditor that moves beyond copilots into a decision-making system. It compresses a 15-hour manual legal contract review into a 12-second map-reduce parallel processing pipeline.
ActionPilot is an AI meeting execution agent. Users upload meeting audio or paste a transcript, the backend transcribes it with Speechmatics and analyzes it with Gemini, and the portal creates meeting summaries, decisions, risks and action items.
Agent orchestration for multi model back end. KCODE Kraken agent. Gemini guided featherless security scanner. Gemini guided tercoms search probes.
Autonomous multi-agent system that converts enterprise meetings into executed actions — voice transcription, RAG, domain-specialized agents, and autonomous execution in one agentic loop. Deployed on Vultr.
An Ai agent that serves to document, summarise or highlight meeting sessions. From team updates to independent projects, alongside receiving images or text submissions; our AI is bound to satisfy KPIs
An autonomous trading agent that ingests live earnings call audio using Speechmatics, evaluates sentiment with a Featherless AI 3-model ensemble, and executes high-confidence trades instantly via Kraken.
We developed an AI-driven cybersecurity platform designed to act as a protective layer for other AI systems, focusing on preventing attacks, misuse, and manipulation of large language models and AI-driven applications.
VEIL is an AI-native financial governance infrastructure that uses collaborative AI agents to evaluate transaction trust, intent, behavioral risk, and compliance before settlement — creating an autonomous trust layer between humans and money.
Iroko AI deploys 5 specialized AI agents that monitor MTN Nigeria's enterprise documents 24/7, detect SLA breaches, compliance risks, and network anomalies in real-time — streaming every reasoning step live so operators see exactly how decisions are made.
AgentiCos is a multi-agent AI orchestration platform featuring self-correcting feedback loops, semantic memory, and real-time collaborative execution. Build and manage autonomous AI workflows with persistent learning and cognitive monitoring.
CXGuard is a lobstertrap powered governance dashboard helps support teams safely launch AI agents by blocking jailbreaks, PII leakage, and refund abuse before customer conversations reach the LLM.
A secure, agentic Physical-to-Logical Digital Twin platform for mission-critical data center infrastructure. Powered by Google Gemini and secured by Veea's Lobster Trap, it translates physical video streams and sketches into active logical topologies.
Incident Brain watches Slack and terminal activity during outages, builds a live semantic timeline, detects repeated failed actions, predicts cascading failures, and drafts post-mortems while keeping sensitive data local.
Autonomous competitive intelligence agent. Enter your URL → Gemini discovers your competitors, scrapes their sites daily, extracts structured signals, and emails you what changed — every inference protected by Veea Lobster Trap.
Gemini-powered governance plane that gates every AI agent tool call, signs the audit trail with cited policy, and meters per-BU spend. Live on real Gemini at agent-sentinel.up.railway.app — Cloudflare for AI agents.
AI compliance guardrail platform that ingests policy PDFs, compiles them into live LLM proxy rules via Lobster Trap, red-teams with 100+ attacks, and self-heals failing rules using Gemini structured output.
NexusGraph AI transforms fragmented enterprise operational data into real-time actionable intelligence using Gemini AI, Neo4j knowledge graphs, anomaly detection, forecasting, and operational reasoning.
Autonomous voice-first xStock trading agent that listens to earnings calls or spoken commands (Speechmatics), runs a 3model Featherless finance ensemble, uses a dynamic Regime Score for selfevolution, and executes paper trades via Kraken CLI,all on Vultr
Polaris turns SOC 2, HIPAA, and EU AI Act PDFs into deployed AI agent firewall policies in 60 seconds. Four Gemini agents read, synthesize, validate, and continuously red-team the policy — closing the loop between compliance docs and runtime guardrails.
Ledger is the governance layer that lets enterprises move AI agent pilots from sandbox to production without losing sleep or money.
Open-source cross-AI verification: Gemini writes code, a 12-vendor adversarial ensemble audits it. Z3-proven INV-15 KV-cache isolation. Every verdict HMAC-signed.
FuelGuard AI is an enterprise operational intelligence platform using Gemini-powered AI copilots to detect anomalies, analyze fuel operations, and provide intelligent risk insights in real time.
Autonomous Android development agent that plans, codes, reviews, builds, installs, launches, checks logcat, and verifies real-device results in one delivery loop.
Forge is an autonomous software-engineering agent that plans issues, fixes code in an isolated sandbox, reviews pull requests, runs validation checks, and returns auditable branches, diffs, and feedback for faster, safer software delivery.
Hinook gives students browser-based access to real physical ESP32 kits hosted on Raspberry Pi. An AI instructor reads their live code, guides them step by step, and highlights relevant lines directly in their VS Code editor.
Autonomous xStocks paper-trading agent powered by Gemini 2.5 Flash reasoning and Kraken CLI execution. Features local/cloud automated system diagnostics, hardcoded risk gates, and JSONL audit logging.
FeatureFlag is an autonomous AI copilot for continuous deployment that uses reinforcement learning, anomaly detection, and multi-agent simulation to automate feature rollouts, instant rollbacks, and enterprise-scale release governance.
SentinelLens is a Gemini-powered Enterprise AI Guardian. It acts as an intelligent proxy that intercepts employee AI usage, detects data leaks (PII, credentials, IP) in real-time, and sanitizes prompts before they reach external public models.
An asynchronous AI orchestration core built with pydantic-ai and the Model Context Protocol (MCP). Features deterministic tool-calling, secure data boundaries, and in-memory latency emulation. Cross-validated on AMD clúster hardware configurations.
StratAI is an AI-powered marketing operating system that helps brands generate market research, strategic planning, content ideas, and business analytics using contextual Gemini intelligence instead of generic AI outputs.
A cryptographic protocol that makes "human approves" verifiable, scoped, and revocable.
Continuous compliance auditing for enterprise AI. A council of five specialised agents audits every interaction your AI produces — in real time — against EU AI Act, GDPR, DORA, PII leakage and prompt injection. Don't pay the fine. Pay attention.
GitHub-integrated AI Agent powered by the Featherless API that autonomously creates, edits, and commits code directly to repositories.
AxiomGuard is a zero-trust Neuro-Symbolic AI Governance Control Plane that secures enterprise workflows. By combining Veea Lobster Trap DPI with AxiomLNN policy verification, it prevents unsafe agent actions via cryptographic Decision Receipts.
MedAgent is a multimodal AI assistant using Gemini 2.5 Flash to transform medical images into structured clinical reports.It provides observations, findings, and explanations for medical education and research purposes.
An AI-powered multi-agent negotiation simulator that models how enterprise contracts are formed in real time using constraint-driven reasoning and structured decision-making agents.
CerberusGuard unifies three MIT open-source primitives into defense in depth for AI agents: Lobster Trap (prompt inspection), PennyPrompt (budget control), and ClawCrate (execution sandbox), with one policy file and one correlated audit trail
bite the news, get the gist, protect yourself from misinformation.
Autonomous AI agent that discovers premium APIs through semantic search, pays for each call with on-chain USDC micropayments via x402, and composes answers spanning 17 data domains — all without a human in the loop.
DevMentor AI is a voice-enabled AI Tech Stack Advisor and Developer Mentor that helps developers analyze project ideas, compare technologies, detect redundant tools, and generate personalized learning roadmaps.
AgentRedTeam is a red-team fuzzer that finds gaps before attackers do.
VeriLex AI is a multi agent legal intelligence platform that analyzes contracts, detects risks, validates compliance, and generates AI powered legal insights for enterprises.
AuditForge - a Gemini-powered agents to audit enterprise codebases, APIs, and configurations against HIPAA, SOC2, and OWASP standards — producing actionable findings, scores, and signed audit reports that security teams and regulators can actually trust.
Mindoor is the trust layer. Governed by Veea Lobster Trap for security. Every patient turn passes three independent security layers before any model responds — and every interaction generates a regulator-readable HIPAA audit PDF mapped to §164.312.
DemoPilot turns any web app URL into a polished, narrated demo video in ~60 seconds. Gemini analyzes the UI, writes the script, Playwright records the browser, edge-tts narrates, and ffmpeg renders the final MP4, fully autonomous, zero human editing.
AgroFlow AI: An organic agriculture supply chain platform with AI-powered crop guidance, real-time weather tracking, logistics management, and multi-role dashboards (farmer, wholesaler, retailer, admin, delivery) built with React, Firebase, and Gemini AI.
An AI-powered multi-agent enterprise financial intelligence system built using Gemini, Streamlit, and advanced AI workflows for financial analysis, anomaly detection, forecasting, and executive decision support.
CGAE is a permissions protocol where autonomous AI agents have to prove they understand a task's constraints and risks before they can participate in economic activities.
Autonomous red-teaming agent that probes LLM deployments across all 6 attack vectors from the Franklin et al. 2025 Google DeepMind paper, with Lobster Trap DPI proxy enforcement and a regulator-readable audit trail.
Context-aware Retrieval-Augmented Generation (RAG) using Google Gemini to ingest multimodal documents, extract figures/tables, and generate professional, explainable reports via orchestrated agents.
80% of SMB founders lack an executive team and trap their own growth. Cortex fixes this with an autonomous AI C-Suite. Driven by Gemini 2.0 & Speechmatics, it gives understaffed businesses a scalable board of directors to unlock up to 35% more revenue.
GEM² Audit OS is an AI governance layer that turns agent actions into contract-bounded steps, audits inputs and outputs at the edge, and produces regulator-readable evidence without requiring humans to manually inspect every AI decision.
Autonomous multi-agent procurement network. 5 AI agents discover suppliers, analyze contracts, negotiate deals and enforce compliance with EU AI Act governance. Reduces RFx cycles 60%, eliminates 90% of invoice exceptions, and automates 95% of approvals.
OpsPulse Sentinel is an autonomous SRE agent that ingests telemetry and deployment logs, filters anomalies via Gemini Flash-Lite, and uses Gemini Pro to deliver a structured root cause analysis with a ready-to-run fix — in under 60 seconds.
An autonomous agent that turns any social profile into a personalised video — from enrichment to rendered output, zero human steps.
A single HTML file that coordinates Claude, ChatGPT, Gemini, and Grok simultaneously. Multi-round AI collaboration, automatic document synthesis (Word, PDF, Excel), persistent memory, self-audit, and external monitoring. No installation required.
OlympusOS is a multi-agent AI orchestration platform that transforms cities into cognitive systems, perceiving crowd crises, coordinating autonomous agents, and resolving emergencies before they escalate.
A finance policy pack on Veea Lobster Trap. AI agent that compares policies against RCSA registers and detects control gaps using Gemini 2.5 Pro — every call inspected, every decision HMAC-audited.
Guardian Overlay is an AI‑powered Chrome extension that helps enterprises and users analyze Terms & Conditions in real time, flagging compliance risks and unfair clauses to ensure safer digital adoption.
5-layer AI agent security platform that scans OpenClaw, Hermes, and Claude Code skills, audits configs, catches skills, audits configs, catches leaked secrets, proxies credentials, and redteams its own detection with LobsterTrap runtime enforcement.
An interactive observability and benchmarking platform for evaluating retrieval robustness in Single-Agent and Multi-Agent RAG systems across SQuAD and HotpotQA benchmarks.
Most meeting AIs summarize what happened. We prevent what shouldn't. A real-time agent that listens during the meeting and flags the moment a decision contradicts your company's legal, capacity, or prior-decision context.
MIRROR is a live AI trading-agent system that runs four Kraken-backed agents, scores them on calibration and net PnL, and promotes better strategies through deterministic replay, Blue review, and ERC-8004 identities.
TAPES is a deterministic governance layer for enterprise AI agents. It uses AST validation to intercept unsafe code modifications by IBM Bob, ensuring 100% production safety while reducing IBM Granite token consumption by 81%.
A zero-knowledge enterprise compliance agent designed to secure AI requests. It safeguards sensitive corporate data and ensures strict regulatory compliance without compromising performance or exposing proprietary information
Scriptless.ai is a voice-driven, AI-powered test generation and execution workspace that connects to your GitHub repo, auto-creates test cases, and runs them in the browser with visual failure analysis.
StartME is an AI company OS with 20 specialized agents orchestrated by a CEO agent — handling sales, marketing, finance, legal, DevOps & more. Built solo by a 17-year-old from Lagos. One founder. A full AI workforce.
"AgentGuard is an enterprise-grade AI agent security monitoring platform delivering real-time threat detection, policy enforcement, audit trails, and governance dashboards for safe, compliant agent workflows."
An adversarial multi-agent court that audits police bodycam recordings in real time. Speechmatics streams the words, Featherless argues both sides, Gemini judges, Vultr runs it. Verdicts cite specific utterances and video frames — defensible by design.
AI-powered port operations copilot that analyzes logistics flow, congestion, and emissions, and provides real-time decision support for smarter, faster, and cleaner port operations.
Meridian turns any video into a queryable knowledge base. Upload a video, ask a question in plain English, and get a precise timestamped answer drawn from speech, on screen text, and what was visually happening at that exact moment.
AquaLens is a web-based freshwater monitoring agent that turns a map-selected lake or water body into a traceable advisory risk brief using Sentinel-2 imagery, deterministic spectral indices, and a constrained Gemini multi-agent workflow.
llmtrace is a self-hosted proxy that traces every LLM spend spike back to the exact deploy that caused it. A Gemini agent detects cost anomalies, investigates your GitHub PRs, and ships the fix autonomously.
When production breaks, Triagix launches autonomous AI agents that detect, triage, diagnose, and resolve incidents in real time before engineers even see the alert. Powered by Gemini, it turns hours of operational chaos into seconds of intelligent action.
SafeArc is a two-agent AI system that detects objects and human zones in a workspace, then generates a collision-free pick-and-place plan with geometry-enforced safety constraints and a live 3D robot arm simulation — all in a browser.
Blitz TraceGrid turns AI-generated repositories into graph-grounded execution stories, scoring behavior confidence, uncertainty zones, replay paths, and security investigation targets.
Shopify for AI agents. Describe your agent, Gemini recommends its financial architecture, then AgentBooks auto-provisions nano-ERP books (BS/IS/CF), filing schedules, and modular cost/revenue tracking. 19 live agents, progressive enrichment as data flows.
PROMETHEUS SHIELD is a self-healing AI security platform that protects AI agents from prompt injections, jailbreaks, and data leaks using Lobster Trap DPI, Gemini-powered attack analysis, and autonomous policy patching in real time.
NeuroSec is a self-evolving AI immune system where defensive agents fight malicious agents like a biological immune system, preventing prompt injection, data leaks, and AI-driven cyber attacks in real time.
An enterprise-grade AI contract analysis platform powered by Gemini 2.5 Flash. ContractIQ extracts key clauses, identifies hidden legal risks, flags one-sided terms, and provides an interactive AI attorney chat to review contracts in ~20 seconds.
CogniBot Simulator is an AI-powered warehouse robotics simulator that uses Google Gemini to understand scenes, generate task plans, monitor execution, and create training videos for safer and smarter automation workflows.
Enterprise AI Firewall powered by PolicyThread, real-time compliance monitoring, intent verification, and cryptographic audit trails for AI agents.
Aegis OS is an AI-powered digital nervous system that detects, analyzes, and coordinates autonomous emergency response operations in real time.
VoxProof is a runtime security and adversarial testing platform for AI voice agents that detects prompt injections, tool abuse, data exfiltration, and voice-layer attacks in real time using hybrid AI + deterministic policy enforcement.
TrapLedger is a pre-signing payment enforcement gateway for autonomous AI agents. It evaluates agent-initiated x402 payment requests against enterprise policy before any wallet signing, blocking unsafe attempts with a full audit trail.
Four Gemini agents autonomously onboard B2B clients. Upload a contract PDF, paste a brief, and agents research the client, send personalized emails, build project plans, flag risks, and handle intake submissions without human triggers.
AEOS is a runtime-governed multi agent enterprise operations platform that autonomously coordinates workflows, incident response, multimodal reasoning, adaptive recovery, and operational governance through collaborative AI agents.
PulseGuard: An enterprise-grade AI governance and privacy orchestrator built for zero-trust data
Submit a ticker. Five agents read the 10-K, 10-Q, and earnings call, then argue. Bull and bear cite every claim to a primary source. A reconciler ranks where they materially disagree. One click to verify against SEC text or call audio.
AXIOM deploys five AI agents that argue over your business problem and issue a binding decision in under 30 seconds — then automatically improve themselves after every run.
Reef is the signed supply chain for MCP servers, plus the audit your insurance company needs to cover an AI agent fleet. Blocks the April 2026 Anthropic MCP RCE at the handshake. Outputs a signed, Munich Re-grounded RIA your underwriter can price.
When attackers target your AI agent, most systems block them. MIRAGE lets them in — silently switching to a honeypot that feeds convincing fake data. Zero real bytes leaked. Full attacker profile built. Powered by Veea's Lobster Trap DPI.
ZeroDay is an autonomous agent that takes a GitHub repo and a CVE identifier and ships a tested, reviewer-ready pull request in 42 seconds. It reads the repo, if vulnerability is reachable, generates the patch, predicts test outcomes, and writes the PR.
his child project is a hybrid social networking platform that combines the professional ecosystem of LinkedIn with the fast paced interaction style of X (Twitter).
App-first AI agent for civic incident intake, report extraction, department routing, area alerts, and trackable municipal response.
An AI-powered visual modernization platform that maps complex codebase architectures and instantly refactors legacy scripts into production-ready, modern code.
This project uses the BOB Framework for AI-assisted development. DocRAG-MD is a lightweight, open-source medical question-answering system.
BilimForAll is a gamified "Duolingo for professions" powered by a multi-agent Gemini 3.1 system. It features automated onboarding, content generation, voice roleplays with AI mentors, and Context Caching, slashing enterprise API costs by up to 85%.
AI assistant that quietly joins your calls, listens in the background, and turns every conversation into structured knowledge you can actually use later.
PrimaVista is an AI copilot for redevelopment companies, allowing teams to seamlessly collaborate with specialized agents to automate site research, zoning analysis, 2D layouts, and 3D conceptual designs for building transformations.
Ephemeros is an ephemeral context bridge for IBM Bob, letting Bob fetch scoped enterprise context through MCP, use it for better code generation, then clean it up without broad or permanent private-network access.
Real-time incident response dashboard powered by IBM Bob. It analyzes logs, deployments, commits, and runbooks to detect root causes in seconds, suggests fixes, and auto-generates post-mortems for faster recovery.
GitPilotAI is an AI-powered developer onboarding platform that helps engineering teams understand GitHub repositories faster through intelligent repository summaries, onboarding roadmaps, important file analysis, and repository insights.
App-first civic reporting platform that turns resident issues into structured tickets, AI-assisted routing, area alerts, and trackable municipal action.
A Bob IDE skill pack + GitHub Actions agent that blocks PRs which ship HIPAA, SOC 2, PCI, or GDPR violations. 30 controls, 4 frameworks, $0.03 per PR. Replaces the $50K external audit + 6-month cycle with a 4-minute check. Built end-to-end with IBM Bob.
Vanguard Milano is an autonomous logistics AI that reroutes freight around labor strikes in Northern Italy. Powered by Gemini 2.5 Flash and Vultr, it features real-time threat detection and instant X402 stablecoin settlement to secure backup capacity.
CORTEX (COgnitive Reasoning and Task EXecution) is an AI-powered automation platform that enables enterprises to capture, structure, and execute complex workflows across desktop and web applications without requiring APIs or integrations.
NexusIQ is a multi-agentic corporate upskilling system that uses AI tutors to provide personalized, project-based training. It features automated curriculum generation, real-time agent monitoring, and adaptive evaluations for employees.
Grants for Me connects SMBs with unclaimed government grants. Dynamically crawls scattered portals to extract live funding data. Built via IBM Bob, it instantly matches users with high-win grants in plain English.
An autonomous, solo-engineered multi-agent personal assistant and study companion featuring a custom glassmorphism interface and Python backend. It implements a dedicated MCP server reducing context-window overhead through on-demand tool discovery.
An advanced, stateful simulation sandbox where a multi-agent swarm built on Google Gemini collaborates with users via Speechmatics real-time voice dictation to dynamically build laws, enforce logical consistency, and simulate a living story universe.
Bob Agent is an AI-powered CLI coding assistant built with IBM Bob and watsonx.ai. It generates tests, documentation, and code reviews from natural language commands — helping developers ship quality software faster.
Fuzzy RAG is an explainable Retrieval-Augmented Generation system that combines vector similarity with fuzzy logic to provide context-aware document ranking.
AI Startup Operator is an AI-powered platform that helps entrepreneurs validate startup ideas, analyze markets, manage tasks, and generate business insights using intelligent automation and real-time AI assistance.
IT is a security guard for AI in hospitals. When a doctor asks an AI about a patient, it checks both the question going in and the answer coming out blocking things like leaked Social Security numbers or hidden hacking tricks.
This is Conductor — a cross-repo consistency agent built on IBM Bob. One change request in, a consistent fleet out.
AgenticRepo is an GitHub-native AI agent that monitors repositories, analyzes CI/CD workflows, detects regressions, correlates suspicious commits, generates insights, and creates automated fix pull requests using IBM Bob-powered intelligence.
trtretretretretretret tret ret et ret retret ret ret re
OSS Preflight helps a developer turn an app idea into an evidence-backed open source starting point: ranked package recommendations, an Evidence Passport, and a scaffolded starter with a smoke test.
LegacyLift uses IBM BOB to analyze legacy enterprise systems, identify modernization risks, map architectural dependencies, and generate a prioritized upgrade roadmap through an interactive risk dashboard.
VendorIQ is an AI-powered procurement intelligence platform where 13 specialized AI agents debate enterprise vendor proposals across multiple rounds before delivering an evidence-based final recommendation.
Ticket Inteli turns messy customer support tickets into structured engineering action briefs, reducing support-to-engineering handoff time and helping teams respond to customer-impacting issues faster.
Autonomous multi-agent AI system that trades tokenized U.S. stocks (xStocks) on Kraken using Google Gemini 2.5 Pro reasoning and real-time market analysis.
Context Drop is an AI-powered repository intelligence platform that analyzes codebases, generates architecture insights, explains system flows, and assists teams with onboarding, ticket analysis, PR reviews, and developer handoffs.
Bob's Twin proves AI-migrated Python code didn't break behavior. bump-pydantic fixes 80% of v1→v2 syntax — Bob's Twin catches the silent 20% (Enum, Decimal, validator drift) via record-replay and hash-chained audit. EU AI Act Article 12 ready.
Live adversarial wargame for AI agent security. AI Attacker (Gemini) vs Dual-Layer Defender (Lobster Trap + Gemini). Scores risk in dollars, maps to 6 compliance frameworks, auto-hardens policy in just a minute.
Got a buggy deployment on Vultr? Ask mixer to fix it. Server down? Ask mixer why. Need to onboard a new team member but you don't have what it takes? Ask mixer to do it. Mixer is an agentic runtime built for the enterprise.
BobGuard is an AI-powered code security auditor that scans repositories for vulnerabilities, maps findings to OWASP categories, and uses IBM Bob to explain risk and generate actionable remediation guidance.
AI-powered on-boarding accelerator that analyzes codebases, maps architecture and workflows, and generates actionable documentation and graphs for new developers.
BM BOB RepoPilot is an AI-powered repository assistant that analyzes codebases, explains files, answers developer questions, and helps teams understand, debug, and improve projects faster.
Spec-to-Ship converts plain-English software feature requests into structured engineering tasks and automated GitHub pull requests using IBM Bob IDE, watsonx Orchestrate agents, 7 GitHub API automation. Demo: https://spec-to-ship-pied.vercel.app/
Autonomous AI pen testing and patching agent system, making elite cybersecurity accessible to all companies that require it.
TAPES wraps IBM BobShell (Granite-13b) in a 5-stage governed pipeline: intent → frozen contract → retrieval-shaped context → adversarial patch validation →sandboxed execution. 81% token reduction, 100% protected file safety across 8 adversarial scenarios.
DevAgents is a clean, web platform where you can run AI agents directly in your browser. No sign-up. No backend. No data collection. Just paste your API key and go.
amneAI uses IBM Bob Shell to turn any GitHub repo into a plain-English codebase guide for your future self. Built for vibe coders who ship fast with AI but can't explain their own code the next day. Made of Bob, by Bob, for Bob.
An AI‑driven multi‑agent platform that mentors, evaluates, and rewards developers while they solve Data‑Structures‑and‑Algorithms challenges, using Gemini Flash for real‑time reasoning and Web‑3 token/NFT incentives.
CodeOnboard is an MCP server that turns any GitHub repository into an AI-powered developer onboarding guide with architecture, setup, key modules, and first-week tasks, generated in seconds using IBM Watson.
OrkestrAI is a multi-agent AI platform that accelerates hackathons. It uses 6 specialized AI agents working sequentially to autonomously plan, architect, and generate a complete project codebase and pitch materials in under 90 seconds.
Qrew gives solo founders a complete AI team. Describe your startup idea and 5 specialized agents — Alex, Sam, Jordan, Morgan, and Riley — research, strategize, design, build, and deploy your company in one session. Built with IBM Bob.
Legacy COBOL Payroll Modernized: AI-powered transformation of a 1980s payroll system into a modern full-stack web application using IBM Bob.
ramen ai intercepts JSON tool-calls at the OS boundary. It is a stateless, pre-execution semantic firewall that mathematically forces autonomous agents to comply with the EU AI Act, HIPAA, and OWASP standards, ending checkbox compliance forever.
7 Gemini specialist agents resolve e-commerce damage claims in <10s, then ship a Stripe-Radar-style Trust Score (0-100, 6 factors) . Sierra-style hard-rule Supervisor + pHash fraud gate + EXIF deepfake check + deterministic amount sandbox.
Aegis Pro is an 8-agent AI swarm that detects supply chain crises and triggers autonomous mitigation actions in under 60 seconds — powered by Gemini 3.0 Flash and Veea Lobster Trap edge infrastructure.
RepoMind is an AI-powered codebase assistant that analyzes GitHub repositories, explains code, generates docs and tests, detects risks, and visualizes architecture using IBM Bob AI to help developers understand projects faster.
Agrishop-pro is the platform I built to help family business and farmers - step into the digital world without losing any of that warmth. It gives farmers a personal dashboard to manage their equipment and orders. Rooted in family. Designed for farmers.
PromptGuard AI is an enterprise agent firewall for LLM apps. It sits between the users, models and agent tools, then scores prompts, model outputs, uploaded text and tool calls before allowing the action to proceed.
CodeSentinel is an IBM Bob-powered codebase intelligence platform that helps developers understand repositories faster, detect risks, generate test/documentation suggestions, predict PR impact, and export release-ready PDF reports.
A multi-agent AI system that autonomously scans defense contracts, detects every risky clause (including hidden ones), and delivers instant mitigation actions — built on anti-hallucination architecture for zero false confidence.
Software MRI X-rays legacy codebases nobody understands anymore, exposing hidden architecture, blast-radius predictions, tech-debt hotspots, and AI-powered modernization intelligence. Turn decades of tribal knowledge into observable reality.
FlowFix turns failed logs and scripts into structured AI-generated debug runbooks with root cause hypotheses, fix steps, verification checks and reusable troubleshooting notes.
An AI-powered onboarding platform that scans large GitHub repos and turns legacy codebases into clear setup guides, architecture summaries, and contributor roadmaps for new developers.
Aegis is an AI firewall proxy that sits between enterprise AI agents and LLM APIs.
TariffGuard AI is a multi-agent system powered by Google Gemini that automates tariff classification, regulatory compliance, and customs audits, reducing audit times from days to minutes with 94%+ accuracy.
A cognitive, identity-aware agent that operates at machine speed RSAI ingests your company's proprietary negotiation DNA and deploys a fleet of elite sales clones to autonomously identify, qualify, and convert prospects 24/7 with enterprise-grade security
TechEx AI Command Center is a multi-agent enterprise AI orchestration platform that coordinates specialized AI agents for analytics, finance, operations, workflow execution, and executive report generation in a unified intelligent dashboard.
VoiceBroker AI is a fully autonomous voice-powered trading assistant that converts natural speech into intelligent trading actions using Gemini AI, Speechmatics, Kraken APIs, and Supabase.
BilimForAll is a gamified "Duolingo for professions" powered by a multi-agent Gemini 1.5 system. It features automated onboarding, content generation, voice roleplays with AI mentors, and Context Caching, slashing enterprise API costs by up to 85%
Nexova AI is an enterprise AI operations platform that combines business analytics, AI-powered forecasting, inventory intelligence, contract analysis, and a real-time AI assistant into a modern SaaS dashboard powered by Gemini AI and Supabase.
Win more deals customer and VC deals. Stop guessing why you lost.
Autonomous infrastructure for the Agentic Economy. fervoAI Treasury Agent hits live government S2S APIs to find, score, and route federal grant execution via stateful multi-agent swarm orchestration. Human approval is the only remaining blocker.
Repo Guardian is an intelligent, automated repository compliance engine and architectural guardrail built to bridge the gap between AI-driven rapid development and enterprise-grade software engineering standards.
Transforming startup ideas into deployable MVPs using autonomous AI agents.
OnboardIQ turns any GitHub repo into an interactive onboarding guide in under 2 minutes. Powered by IBM Bob's agentic codebase analysis, it generates an architecture map, developer checklist and domain glossary, to help faster productivity on codebases.
SentinelIQ is an in-line security proxy that intercepts AI agent traffic, enforces YAML policies in real-time, detects threats, and provides Gemini-powered compliance auditing with cited answers from enterprise data.
CityMind is an autonomous AI crisis command center where multiple specialized AI agents collaborate in real time to manage city emergencies, simulate cascading failures, and generate recovery strategies using a live digital twin system
Multi agent decision intelligence - 6 agents with Chanky The Strategy Architect Objective Logic Vizi The Risk Mitigator Kavi The Value Optimiser Sri The Innovation Catalyst Jupi The Culture Guardian Mars The Conductor
This is multi domain support system which help to solve multiple tickets, reduce hellucination and This is RAG based system.
PRISM is a hackathon project that adds a semantic risk-analysis layer on top of pull requests. The system has three deliverables: a CLI, a FastAPI backend, and a Next.js dashboard. This plan covers only the CLI — the developer-facing entry point.
AcademiaGenie is an AI-powered assistant that analyzes student CVs to find high-match professors globally, generate hyper-personalized cold emails, and provide actionable roadmaps to bridge academic profile gaps for graduate admissions.
Atlas Sanctum is a multi-agent AI command system that transforms enterprise data into autonomous decisions and real-world actions using intelligent reasoning, multimodal analysis, and collaborative AI workflows.
Aegis Pro is a fully autonomous supply chain crisis management agent. 7 AI agents monitor live maritime intelligence, Kraken market signals, and geopolitical data — delivering crisis detection and ranked action plans in under 2 seconds.
An autonomous AI-Agent system leveraging IBM watsonx.ai for high-precision genomics and CRISPR analysis to address health challenges in Sub-Saharan Africa.
Isolated Agents SDK is a framework for running AI agents in secure, isolated containers locally
Apex is an autonomous multi-agent sales pipeline that discovers, and engages business leads across US markets — entirely without human intervention. Built for solopreneurs and small teams who need enterprise-grade outreach without the headcount.
AgentRx audits any AI agent endpoint across structure, behavior, and compliance using the Thread Suite APIs. Paste your agent URL, get a Reliability Score in seconds. Built with IBM Bob.
Autonomous AI navigation agent for Milan 2026 Winter Olympics real-time crowd monitoring at 14 venues, smart routing, and Gemini-powered chat assistant deployed on Vultr.
Transform your support operations with an intelligent ticket management system that leverages AI to prioritize workloads, predict trends, and empower decision makers with actionable insights across all organizational levels.
is a token budget management tool for Large Language Models (LLMs)
An automated DX tool that crawls repositories, minimizes token overhead, and leverages IBM Bob to auto-generate comprehensive onboarding architecture guides.
ARCHON is an AI engineering intelligence platform powered by IBM Bob that helps developers understand codebases, analyze architecture, predict code impact, debug faster, and manage complex software systems using repository-wide AI reasoning.
A multi-agent M&A due diligence system where AI agents (Researcher, Analyst, Red Team, Synthesizer, Verifier, Orchestrator) collaborate in real time to deliver a board-ready acquisition brief, sourced claims, conflict detection, and integrity scoring.
Reckon gives every codebase a memory. It auto-generates a MEMOIR.md per module from commits, PRs, and postmortems — then blocks code changes that would re-open past incidents, right inside IBM Bob.
APREP is a semi-automated AI agent evaluation platform that tests safety, honesty, prompt adherence, semantic accuracy, and performance through configurable workflows, reusable question sets, and AI-assisted behavioral analysis.
SemAuth enforces Intent Integrity the authorization property every existing IAM system assumes but never verifies. It intercepts LLM agent tool calls,detects CVIC attacks that pass OAuth and Cedar, and gates RFC 8693 token issuance on verified reasoning.
XIO ProofOps Agent turns decks, contracts, policies, and voice transcripts into risk-ranked findings, verified citations, redlined safer language, hash-bound human approvals, and a downloadable DOCX proof pack. Compliance teams ship evidence, not chat.
Turn every IBM Bob session into replayable memory. CrumdBob captures Bob's repo analysis as a 9-file CRUMB pack with proof chain, SQLite-backed cross-session history, FastAPI dashboard, LLM-powered insights, and enterprise observability.
WingMan makes phone calls on your behalf. Speak your message, it calls the person, handles the conversation, and sends you a WhatsApp summary — so you never have to make an awkward call again.
Test tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tesTest tes
dghhhhhhdghhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhdghhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh
MarketLeadOS is a 4-agent AI system that autonomously posts ads, tracks website visitors, builds lead personas, and sends hyper-personalized emails — all controlled via 2 Telegram commands. Zero humans. Infinite learning.You said: Long Description*
ReelSights AI creates Governed Cognitive Clones that operationalize expert revenue knowledge. Using Gemini 2.5 Pro and Vultr-backed middleware, we deliver 24/7 autonomous sales execution with CISO-ready auditability and human-in-the-loop oversight.
Solve NP-Hard logistics in 30 seconds using Quantum AI, Speechmatics STT, and live weather/traffic/carbon enrichment at zero cost.
Autonomous AI agent that analyzes legal contracts end-to-end. Extracts clauses, scores risk HIGH/MEDIUM/LOW, suggests professional rewrites, generates executive report, and answers questions via chat. No lawyer needed.
An autonomous incident response voice agent deployed on Vultr that bypasses slow email alerts by calling engineers. It uses Speechmatics for real-time STT and Gemini Flash function calling to explain threats and secure verbal patch authorization.
An MIT-licensed role-aware memory layer that lets planner, coder, and reviewer agents share context through namespaces — not prompt-stuffing. SOTA: 99.4R@10 on LongMemEval-S.
DataReady is a 4-agent Gemini-powered multimodal audit that tells you why your AI BI rollout will fail — by reading your CSV, dashboard, and data dictionary together and scoring semantic-layer readiness before you connect a copilot.
Kiara is an Android AI agent that can understand the current screen, operate apps through accessibility, and complete tasks like messaging, email, navigation, reminders, and event-based actions using local or cloud AI
An ai agentic system that controls the computer like a human being. It has access to mouse, keyboard controls and DOM tools, to use the computer precisely as a human being would
Governed AI agents for smart-grid operations, combining Gemini-ready diagnostics with Lobster Trap-style safety policy enforcement.
OmniMind is a sophisticated, full-stack "data mind" application engineered by carolinesedurica-ux. Designed as both an internal AI powerhouse and a dynamic data dashboard, it bridges the gap between raw information and actionable business intelligence.
Company Brain turns scattered enterprise documents into a living knowledge graph. Ask who owns a process, find the go-to expert, and surface knowledge gaps your organization didn't know existed: all grounded in real sources, never hallucinated.
AluminatiAI GreenTune is an autonomous AI energy optimization platform that uses multi-agent systems and real-time GPU telemetry to reduce the cost, power usage, and carbon footprint of enterprise LLM training workloads.
AuditIQ deploys 6 specialized AI agents to autonomously audit AI-powered web apps. It catches prompt injection, PII leaks, XSS, and security gaps traditional QA misses. Powered by Gemini 2.5. Built for teams shipping AI products.
Lobasters transforms AI conversation into autonomous creation. It provides a rigorous Proving Ground for enterprise agents to plan, reason, and execute tasks, with built-in adversarial testing and automated grading to ensure production readiness.
AI Daily Life Optimizer is a Streamlit-powered dashboard that combines focus detection, activity forecasting, weather insights, and Google Fit data to help users plan smarter routines, boost productivity, and improve overall wellness.
A production-ready multi-agent AI framework inspired by ant colony intelligence
Paxis gives EU enterprises a free compliance OS to track Scope 3 emissions and dispatch CSRD questionnaires to their supply chain; suppliers get free EU AI Act and carbon tooling in return, funded by the enterprises who need their data.
Vantage Point is the observability layer for the ActionPilot ecosystem, providing real-time telemetry and analytical oversight for high-throughput enterprises and asynchronous multi-agent workflows in the cloud.
Pantheon is a real-time security operations center for enterprise AI agents. Powered by Gemini 2.5 Flash and Veea Lobster Trap, it monitors, inspects, and red-teams every agent interaction with live threat detection and full audit trails.
SENTINEL is an AI governance layer built above Veea Lobster Trap. It combines deterministic DPI enforcement across 14 policy rules with Gemini semantic reasoning — and a live operator dashboard to review, escalate, and decide on every AI agent incident.
Pick one stock you believe in. WhaleGarden's AI agents build a diversified 16-stock portfolio around it, track performance with SEC-mirror filings, and settle on Base via wNEWS tokens. Tree vs garden — see if Gemini AI diversification wins.
Real-time AI agent trading platform with voice commands, paper/live trading, and exchange market data.
Six autonomous AI agents analyze any contract end-to-end — extracting clauses, scoring risks, generating executive briefings, and self-auditing their findings — all powered by Gemini 2.5 Flash, with zero human prompting.
Praxis is an AI Chief of Staff for SMB CEOs that automates executive updates, investigations, team coordination, and investor reporting by connecting tools like Slack, Gmail, Stripe, and HubSpot.
Multi-Agent Contract Intelligence AI Agent Turn a 3-day legal review into 30 seconds using 5 specialized AI agents.
Autonomous dataset engineering platform that discovers sources, extracts content, filters quality,& exports production-ready AI training datasets fully orchestrated with multi-provider failover, Celery workers,LangGraph pipelines,& real-time observability
VOLNARA is an AI-powered hardware design platform that transforms natural language prompts into manufacturable PCB designs, complete with schematics, routing, BOMs, simulations, and production ready files for modern electronics development.
Axiom is an autonomous academic due diligence agent that automates systematic literature reviews. Powered by a multi-agent LangGraph architecture on Vultr and Featherless, it analyzes papers, maps controversies, and drafts APA 7 reports in minutes.
An enterprise SaaS transforming car data into immersive showrooms. Built with a 7-agent Gemini pipeline orchestrated by GCP Workflows and hosted on Vultr. Features real-time multimodal voice agents and RAG for a data-sovereign dealership ecosystem.
Atmos is a music experience that turns a simple moment into a visual, playable soundtrack journey.
3 Gemini-powered agents that onboard any employee in minutes. Auto-provisions tools, builds a personalized 30-60-90 day plan from your handbook, and answers HR questions 24/7. No manual work.
Cognitive observability for autonomous AI agents. Real-time six-dimensional monitoring, pre-emit intervention, regulator-ready audit. Industry-agnostic. Patent Pending. Built on Gemini Flash + Veea Lobster Trap.
AegisNexus AI is a real-time AI governance and prompt security platform that detects prompt injection attacks, analyzes threat levels, enforces safety policies, and visualizes adversarial simulations through an immersive cyber-defense dashboard.
An AI-powered contract review platform using a multi-agent swarm and Gemini's 2M context window. It automates clause extraction, risk scoring, and redlining with human-in-the-loop oversight for high-fidelity legal intelligence.
An intelligent enterprise system that utilizes Gemini to monitor, diagnose, and repair server infrastructure autonomously. It ensures business continuity by neutralizing cyber threats and automating resource scaling via X402 Payments.
AI system for enterprise intelligence and decision support across business operations.
AsystQA AI Command Center is an AI-powered enterprise digital twin platform that uses autonomous AI agents to simulate operations, predict risks, monitor infrastructure, and forecast business impact before failures occur.
NeuroSentinel is an AI agent security and governance platform that helps enterprises safely use AI with internal documents by enforcing IAM, RBAC, policy checks, secure mail control, audit evidence, and human approval.
EraSandbox AI uses Gemini, Imagen, and Veo on Vertex AI to help companies discover future product ideas, rank opportunities, generate MVP blueprints, and create real concept images and videos.
VendorIQ is an AI-powered procurement intelligence platform where 13 specialized AI agents debate enterprise vendor proposals across multiple rounds before delivering an evidence-based final recommendation
Codexa uses Gemini AI to transform GitHub repositories into interactive system maps with AI tutoring, flow tracing, guided learning paths, and architecture storytelling to help students or developers understand complex codebases faster.
Friday is an autonomous AI assistant that remembers context, orchestrates 30+ specialized agents, and uses voice, tools, and proactive reasoning to turn complex workflows into finished actions.
A multi-agent network using Gemini and LangGraph to monitor grid telemetry. It catches sudden solar shocks, overrides standard math solvers when hardware limits are hit, and outputs clear JSON logs to keep the system stable .
An autonomous SRE agent powered by Gemini that closes the semantic gap in AIOps. It ingests telemetry, deployment logs, and cluster architecture to perform root cause analysis and generate executable remediation commands in under 60 seconds.
local-first agent orchestration runtime. it acts as the user proxy, AI agent that is trained on the user's identity, local machine, emails and converts them into trainable datasets. a personal AI proxy (ghost)
sdfghbjnbliujhisshfndnsnxuiuigisiigshughjuishugjnujnjingjinuijnjsrggggggggggggggggggggggggggggggggggggggggggggggggggggggggggggedfgdrghfgdrhfgdrhgfhfdhfhrgfghfggh47ty8y9wuy8926879673ijdsafhjbjdbxhblbksjdgbhagbisjgbbjnjvbskbwuiehopiwuhIOHKANWKEHGBHSD bsdkdf
Three keys per entity. One memory protocol. Every framework. Every model. One audit trail via Veea Lobster Trap. Production-proven across 9 agents over 30+ days.
TrustLayer: A Gemini-powered API auditing LLM outputs for hallucinations via autonomous grounding. Secured by Veea Lobster Trap, it restores integrity to AI—showcased via a multimodal Contract Reviewer demo for high-stakes legal and finance workflows.
A Gemini-powered tool that helps companies see how AI agents, LLMs, and answer engines understand their website, trust their claims, and route buyers before a human ever clicks.
Real-time crypto market intelligence platform using a 4-agent Gemini AI pipeline: automated technical analysis, NLP sentiment scoring, trade signals with TP/SL levels, and probabilistic 24h/7-day forecasting.
CGAE is a governance protocol that continuously audits, certifies, and constrains autonomous AI agents before they’re allowed to perform high-impact tasks
MindShield by BrainSNN is a 3D cognitive firewall for enterprise AI, using Gemini analysis, Veea Lobster Trap, and self-evolving defenses to detect manipulation, block unsafe prompts, and fuse multimodal knowledge.
EthiHack is an automated AI security auditing tool that fires 20 adaptive adversarial attacks against any LLM or AI agent, maps findings to OWASP LLM Top 10 + MITRE ATLAS, and generates a professional PDF security report.
A marketing intelligence platform that lets one marketer operate like a ten-person team — by translating natural-language questions into deterministic statistical analysis through a governed semantic layer.
AgentGuard is a real-time AI agent governance platform that monitors, detects, and blocks unauthorized AI actions in Jira. It catches AI-originated activity, enforces compliance policies, and generates regulator-ready audit trails.
CogniRoute is an AI orchestration that allocates reasoning acros agents instead of relying on one monolithic model. Heavyweight reasoning models handle planning & verification, while lightweight workers execute scoped implementation tasks.
Real-time autonomous drone swarm simulator with PID physics in C++, LLM strategic orchestration via Gemini AI, TCP telemetry bridge, and live web dashboard — powered by AMD MI300X and ROCm.
Its an agi it grows always it can make tools and use the it can fit any where It learns like a child It simulates the brain and beoynd It compete whole agents It can do anything online and use open sourses Its the begining of future
A powerful Security Operations Center (SOC) dashboard powered by AMD-optimized modular agentic architecture. ZERO-NOISE intelligently analyzes massive log volumes to identify and present only critical anomalies and security threats.
AgentMart is a decentralized Solana marketplace for AI agents where users can discover, test, and buy autonomous AI tools securely using Web3 authentication and on-chain payments.
FactoryFlow is an autonomous predictive maintenance and parts procurement agent for small-to-medium manufacturers
MedTrace AI turns fragmented patient records into a temporal knowledge graph so clinicians in low-resource settings get memory, grounded evidence, and research-style prompts—without replacing clinical judgment or making diagnoses.
Ken hears every word. You understand every one. Ken is a free, self-hostable, open-source AI co-listener that gives real-time, explainable, personalized support during immigration, legal, and medical conversations — built on AMD ROCm.
A stateful neuro-symbolic AI narrative engine for stories that uses structured state as the source of truth. It generates stories through DAG-based scene execution, selective context propagation, incremental verification, and validated state updates.
TurtleTalk is a voice companion that helps kids reframe hard moments into actionable missions and helps parents build a deeper connection with their kids. Our mission is to make education easy and accessible for everyone.
AMD-Link is a four-stage multi-agent pipeline (ingest → extract → route → check) that turns a natural-language prompt and a raw .kicad_pcb into a routed board, powered by a local-Ollama RAG layer with grounded per-field extraction and self-RAG critique.
BrainOS turns Slack, docs, PDFs, and diagrams into a reconciled knowledge graph. Live Slack integration answers @BrainOS queries in-channel and exports portable SKILLS.md context for Claude, GPT, Cursor, and other AI agents.multi-modal on AMD MI300X.
Real-time football intelligence for fans and broadcast teams, powered by agentic match research, tactical vision Q&A, and AMD-ready ROCm/vLLM infrastructure.
SafeGuard AI is a multi-agent system for the AMD Hackathon. Using CrewAI, it analyzes IoT sensor data to detect anomalies. A safety agent then drafts repair protocols. Optimized for AMD Instinct MI300X GPUs and the ROCm stack.
Transforms a 10min EA questionnaire into governance-grounded, Jira-ready roadmaps. Agentic pipeline: Graph RAG (44 domains,1,400+ capabilities) → DRL prioritisation → Qwen-72B on AMD MI300X via ROCm → compliance verification. Built on LangGraph + Neo4j.
SentinelAI is a hackathon-grade, production-shaped autonomous Security Operations Center. It continuously ingests telemetry through collector agents, normalizes and enriches events, runs multi-modal detection.
Automato is a Vision-Native RPA that automates software like humans. Replacing fragile code with Qwen 3.6 AI, a pinecone database, and pygetui allows anyone to use plain English to build cross-platform workflows that are truly unbreakable.
A multi-agent AI framework for clinical reasoning that evaluates iterative decision-making workflows using coordinated AI agents to solve, critique, and refine diagnostic reasoning on benchmark healthcare question-answering tasks.
BiasharaMind is an AI-powered business consultant for SMEs, turning business assessments into clear diagnostics, priorities, growth roadmaps, and practical reports to help owners make better decisions.
Multi-tenant SaaS that converts Discord user profiles into 2048-dim semantic vectors via AMD-accelerated OSS 120B and Qdrant, enabling privacy-isolated partner matching across roleplay, book clubs, and gaming communities no custom infrastructure required
5 expert AI agents (PM, Developer, Critic, Finance, Security) debate any business idea in real-time using Qwen2.5 on AMD MI300X GPU via vLLM, delivering structured analysis with GO/NO-GO decision and voice summary.
A platform where AI agents learn skills from certified AI teachers. Enroll, study structured courses, chat with an LLM teacher, and earn certificates. Works with Claude Code, OpenClaw, or any REST client.
CogniCore transforms meetings into production-ready workflows using AI. It captures discussions, extracts decisions and tasks, then orchestrates development, governance, and execution automatically in one unified platform.
CropWhisper is a multimodal AI agent that diagnoses crop diseases and nutrient deficiencies from photos, then delivers a plain-language, prioritized action plan — built for farmers worldwide who have a smartphone but no agronomist.
AI agent built on Gemma-4-E4B, trained via GRPO Reinforcement Learning for advanced multi-hop reasoning. It dynamically searches the web, executes code, and synthesizes complex data into comprehensive reports while preserving vision capabilities.
OpsTune is an AI-powered industrial incident analysis system that transforms unstructured operator reports into actionable intelligence using a fine-tuned LLM running on AMD hardware.
An AI-powered slide deck generator that streams fully-designed, web-native HTML presentations in real time — complete with animations, syntax highlighting, and vision-model layout auditing.
GreenChain is a multi-agent AI system that audits supply chain carbon footprints in seconds. Upload shipping data and three AI agents extract shipments, calculate CO₂ emissions, identify hotspots, and generate a green sustainability roadmap.
An AI system that analyze geospatial data and community surveys to predict childhood/community diseases outbreak,identify root causes and generate targeted ministry of health response strategies specifically for vulnerable regions.
LeadOS is a white label agentic AI platform that engages leads through chat or voice, qualifies them with business context, scores intent, and routes the best opportunities to human teams.
We designed and built a RAG based AI agent which helps user to know his legal rights and learn new laws We designed and built a RAG based AI agent which helps user to know his legal rights and learn new laws
GhostTrace AI is an autonomous cyberattack investigation platform powered by AMD Instinct MI300X GPUs that uses AI agents to detect threats, reconstruct attack timelines, analyze multimodal evidence, and generate forensic intelligence in real time.
Agentic GraphRAG system mapping startup policy docs against GDPR, EU AI Act, NIS2 & DORA using Neo4j knowledge graphs + LangGraph agents + Qwen3-4B-Thinking on AMD MI300X. Finds cross-regulation conflicts flat RAG cannot detect.
Project Aura is an AI-powered forensic platform accelerated by AMD Instinct™ MI300X. It utilizes the Qwen-7B model via ROCm™ to analyze raw forensic artifacts and generate automated, structured investigative reports.
AMD-CineMatch is a decoupled AI agent that analyzes user sentiment to provide personalized Netflix recommendations. Optimized for AMD Instinct™ MI300X and ROCm™ 6.0 it demonstrates a scalable bridge between open-source models and high-performance silicon.
AI-assisted port operations platform that helps reduce truck queues, berth and yard bottlenecks, idling, fuel burn, and CO₂ impact through dashboards, simulation, Copilot guidance, and explainable recommendations.
VisionGuard is a real-time industrial visual inspection system that uses Qwen-VL on AMD MI300X via ROCm/vLLM to detect product defects, trigger operator alerts, generate reports, and support factory-specific adaptation workflows.
An agentic operating system that ingests global data (news, satellite, financial signals), reasons with AI agents, and produces live, decision-grade intelligence.
AMD-hosted multi-agent research reproducibility evaluator that reads papers, resolves arXiv/DOI/GitHub/dataset evidence, critiques gaps, and streams audit-ready reports.
A terminal AI planning harness that turns vague software ideas into model-routed handoffs for coding agents
An intent design engine. The intelligence layer to interface scientific research and physical infrastructure.
ScholarBee is an AI agent that helps students find reliable scholarships based on their profile. It searches trusted sources, checks key details, and ranks results by compatibility.
An AI scientist that autonomously makes any PyTorch model faster on AMD MI300X — achieved a measured 2.93× speedup on Qwen2.5-7B without human input.
AI-powered PC diagnostic system using AMD MI300X, ROCm, and vLLM. Multi-agent CrewAI pipeline diagnoses hardware, software, and network issues with step-by-step solutions via a Next.js dashboard.
DealFlow AI is a multi-agent AI system that performs institutional-grade investment due diligence in minutes instead of days, replacing 3-7 days of analyst work with autonomous CrewAI agents on HuggingFace Inference.
An AI notebook that transforms simple ideas into structured, actionable project plans using dynamic expert agents and multi-modal asset generation.
Read a 2,468-page bill in 27 minutes. Drop a U.S. legislative PDF, get back a structured analysis plus an AI-generated podcast video. Four Qwen models plus Wan 2.2, all hot on a single AMD MI300X. Open-source, MI300X-native, reproducible end-to-end.
Faultline is a multi-agentic platform to simulate how real users fail, abandon, misunderstand, and exploit software before release.
Solo builder shipping AI agent governance on AMD ROCm. Vaara is an open-source Python runtime that intercepts AI agent tool calls, scores risk with split conformal prediction, and writes a W3C PROV-JSON audit trail for EU AI Act Article 14 compliance.
AI-powered crop disease diagnosis and market arbitrage for Africa's smallholder farmers — running on AMD MI300X. Snap a photo, get a treatment plan and the best market to sell at, in English and Swahili.
AI architecture diagramming tool that scans a codebase, extracts verified services and dependencies, then generates an interactive component diagram with animated data flow, evidence-backed architecture insights, and static bottleneck risk detection.
Kernl is a compilation layer that extracts messy operational judgment from Slack threads, tickets, and SOPs, compiling it into versioned, evidence-linked, executable skills files that any AI agent can consume to act like a company's best employee.
AgroFamiliApp: AI conversational agent (voice/text) for Brazilian family farmers, powered by AMD MI300X + Llama 3.1. Access rural credit, weather, markets, and agroecological technical assistance via WhatsApp, Telegram, or WebApp.
Sentinel.AI is an AI-powered autonomous cybersecurity platform that simulates intelligent vulnerability analysis, threat reasoning, and secure document scanning using agentic AI workflows built for the AMD Developer Hackathon.
The AMD Multimodal Workbench is a unified app featuring three specialized modes: industrial defect inspection, an educational medical imaging workflow, and a vision-language assistant. It leverages cutting-edge multimodal models on AMD ROCm. 4
Autopsy investigates why companies fail — and what could have saved them. Six specialized AI agents per mode research in parallel, debate each other's findings, and produce a forensic verdict in ~22 seconds.
KitsuneEngine is a Rust-built browser agent engine that gives AI agents complete DOM sovereignty over the web, not screenshots, not CDP hacks, but full read/write access to live pages, secured by the compiler and gated by human-in-the-loop approval.
Project Hyperion is an offline-first, adversarial multi-agent AI system delivering radiologist-level diagnostic triage. Powered by AMD MI300X, it features a 3-node consensus engine ensuring 100% data privacy and verifiable clinical accuracy at the edge.
An intelligent agentic copilot that automates software migration to AMD ROCm via digital signature analysis, prioritizing real-time performance optimization and code security.
A proactive defense orchestrator powered by an intelligent AI swarm that provides self-healing infrastructure by instantly detecting, debugging, and patching system crashes before they escalate, all safeguarded by strict HITL (Human in the Loop) security.
From street to bankable — AI credit intelligence for African SMEs
Multi-agent AI tool that cross-references professor papers to detect research gaps, maps their trajectory, and generates hyper-personalized PhD cold emails.
Our project gives the AI agent a REPL tool for it to write code in order to explore uploaded documents without having the documents directly uploaded into its context window.
Multi-agent system using AMD MI300X + Qwen2.5-Coder with planning, coding, review, and execution
Hypernetwork that generates task-specific LoRA adapters on-the-fly from few-shot examples, enabling instant domain specialization of LLMs without per-task fine-tuning. Built natively on AMD ROCm/MI300X
A zero-shot multi-agent inspection system for manufacturing. It uses Qwen3-VL on the AMD MI300X to analyze components via live camera, and if it detects an error, a second agent automatically diagnoses the root cause. No model training required.
Aubm is an AI agent orchestration platform that turns a business goal into structured tasks, assigns agents, tracks execution, reviews outputs, consolidates evidence, and generates final reports.
AURA-DSP is an autonomous multi-agent AI pipeline for digital signal processing. Utilizing AMD ROCm and vLLM, it intelligently separates, analyzes, and enhances audio tracks, optimizing complex engineering tasks through automated agentic workflows.
AXIOM is an autonomous SRE agent running on AMD MI300X that triages production incidents, executes code fixes, and opens GitHub PRs in under 90 seconds.
An AI multi-agent system that reviews electrical project descriptions against indexed technical standards, produces traceable compliance findings, and suggests replacement components when a problem clearly maps to a material or protection issue.
An intelligent mechatronic system leveraging the AMD Developer Cloud to provide real-time predictive maintenance and autonomous hardware control for industrial pumps.
PRISM helps AI agents retrieve only the tools they need before acting, reducing prompt bloat, duplicate calls, tool confusion, and latency in scalable agentic workflows.
Pheromone is a 5-agent AI recall OS for grocers. It traces affected products through supply chains, drafts 6-tier customer notifications, and adds first-of-its-kind Reassurance Notifications for unaffected buyers. Runs Qwen3-32B on AMD MI300X.
An autonomous system that combines AI with Chrome, including a "Soldier Agent" hive architecture and persistent SQLite memory, to execute complex web tasks directly via real, authenticated browser profiles.
Task scheduler which control all task based on your schedule with all the pc access . Based used activity it becomes activity i Model too .
An AI marketplace for recyclable wastes — connecting waste providers with recyclers and enabling waste recognition with AI.
ComplyAIgent is an agentic DevSecOps compliance platform — policies to guardrails.
Ask any binary question. A panel of AI analysts debates it in two rounds using live web research, then delivers a calibrated probability with a written synthesis.
AsystQA Command Center is a multi-agent software QA platform that transforms raw code into structured quality reports through specialist agents for planning, code review, security scanning, test generation, and reporting.
AtlasOps coordinates four specialist agents against live Kubernetes incidents—with real observability tools, approvals, Chaos Mesh scenarios, and training on AMD MI300X.
SOCrates is a multi-agent autonomous SOC analyst. Drop in a CVE — three AI agents fetch live threat intel, simulate the full attack path, and produce a MITRE ATT&CK–mapped IR report with a validated Sigma rule. Runs on AMD MI300X. Zero API fees.
4 adversarial AI agents debate every query to deliver calibrated sharp crisp ~50-year strategic forecasts. Fine-tuned Qwen2.5-7B on AMD MI300X with ROCm 7.0. Training loss: 2.5→0.47. Deployed via GGUF Q4 on HF.
A multi-agent AI companion for eating disorder recovery. Delivers a personalized daily card — mood-matched meals, art therapy, color palettes, and progress tracking. Built on AMD GPU with Qwen and FLUX diffusion.
ROCmBench Agent auto-loads Hugging Face models on AMD GPUs with vLLM + ROCm, runs concurrency benchmarks, checks GPU evidence, and recommends the best production deployment config.
EarningsPilot AMD automates financial research using a multi-agent system KPI, Risk, Thesis, Report to synthesize SEC filings and transcripts. Accelerated by AMD Instinct MI300X, it delivers source-grounded, structured investment intelligence in seconds.
AI-powered toolkit for Pakistani freelancers using 5-agent CrewAI, Llama 3.3 70B on AMD MI300X, and Streamlit. Generate proposals, detect scams, calculate rates instantly.
My agent goes from Prompt to GDSII , by doing all the vlsi checks and corrects them using feedback loop . It is based on crewAI orchestration . It supports all the opensource PDKs.
AI-powered career intelligence platform using Qwen3 and live job market data to match users with relevant careers, identify skill gaps, analyze demand trends, and generate personalized learning roadmaps.
AgentOS is a multi-agent AI workflow console that runs planning, execution, validation, and memory recall using Mistral 7B served through vLLM on AMD GPU cloud infrastructure.
why-agent is an enterprised level autonomous root-cause intelligence tool for data teams. It investigates your dataset, forms and tests hypotheses, and returns a structured report with evidence chain, quantified attribution, and next steps.
HIP-Hop is a multi-agent AI swarm that autonomously translates legacy NVIDIA CUDA code into AMD ROCm/HIP C++ syntax, eliminating vendor lock-in using local MI300X compute.
Multi-agent AI pipeline that autonomously triages production incidents. Three specialized agents (Planner → Executor → Summarizer) orchestrated with LangGraph, powered by Qwen2.5-72B on AMD MI300X.
Discover free food near you , after spending all your money on claude code
Agentra is an agentic AI-powered content creation system that uses multiple AI agents to plan strategies, research trends, generate content, optimize engagement, and improve workflows through feedback and memory.
Four AI agents debate your code in real time. SAGE IDE's adversarial boardroom — Architect, Implementer, Synthesizer, Red-Team — resolves via Nash Crucible on AMD MI300X ROCm. The friction is the feature: +12.4% HumanEval+, +8.2% SWE-Bench-Lite.
RAG retrieves. Synthex investigates. A 6-agent pipeline that plans, searches, detects contradictions, and self-corrects — then exposes the full research pipeline as an MCP server so any AI agent can call it as a tool.
An AI-powered document intelligence tool that transforms handwriting into actionable data. It interprets intent, detects errors, and uses agentic workflows to automate form processing—all optimized for high-performance execution on AMD hardware
Real-time AI navigation for the visually impaired using 4 specialized agents on AMD MI300X. Detects objects, estimates depth, understands scenes via VLM, and delivers spoken hazard alerts with priority ranking.
Health Passport AMD turns prescriptions, lab reports, and medical receipts into a patient-owned longitudinal health record using multimodal models on AMD cloud GPUs, then reconciles medications, follow-ups, and timeline entries automatically.
EduSense ingests simulated LMS-style academic records across grades, attendance, assignments, schedules, announcements, and interventions, then routes student queries through intent detection to specialized agent modules.
IntegrationOps AI is an autonomous SAP CPI incident intelligence system that detects runtime failures, retrieves iFlow context, and generates AI-powered root cause analysis with recommendations, confidence scoring, and automated Jira/email outputs.
Career Copilot is an AI-powered platform that automates job discovery and optimizes resumes for ATS. Using Gemini and Agno, it provides personalized career guidance, skill-gap analysis, and automated application tracking to secure internships.
AI-powered career prep platform: search live jobs, parse & tailor resumes to postings, and run voice mock interviews with LLM feedback — all locally via Ollama, with no database or accounts required.
An agentic debugging assistant that helps developers triage AMD/ROCm, PyTorch, Hugging Face, and deployment errors from logs, then generates safe fix plans and verification steps.
It is a lossless neural compressor for high energy physics data. Using a novel float32-aware embedding (TDTEmbedding) and trained on an AMD MI300X GPU, it improves compression by up to 28% over LZMA-9 on ATLAS datasets.
Med-Audit-Swarm is an autonomous AI swarm powered by AMD MI300X that prevents fatal prescription errors. It extracts messy EMR data to detect lethal drug interactions with 100% precision, eliminating alert fatigue with zero hallucinations.
A guided web app for cleaning documents, fine-tuning Gemma with LoRA on AMD MI300X GPUs, and deploying a Try-It inference endpoint without touching a terminal. For non-technical users who want to fine-tune a small, local model, this does it all for them.
Boundary Forge helps enterprises safely deploy any LLM by automatically finding model failure boundaries, benchmarking risk, and converting failures into runtime guardrails. Demonstrated with Qwen 2.5-72B on AMD Cloud.
A multi-agent collective intelligence for DevOps orchestration and automation, powered by the GPUs of the AMD Developer Cloud.
jkopjojiojjjoijiojjoijojiojiojoijojoijojoijojojoijojoijojojoijiojojijojojoijoij oji oi joi jo jo. joi jo joj oijo joj oij oi joi jo joi joi joi jo jo joi jo joij oij
SwarmTrace is an open-source observability toolkit for LLM agent swarms. Trace multi-agent calls, enforce token budgets, detect prompt regressions, and reduce tool token overhead by 95% — all with a single Python decorator.
A research simulator testing how small vision-language models control a drone in hazardous 3D environments using camera frames, telemetry, and high-level actions.
An Agentic AI tool that orchestrates Blender and IFCLibrary to automate 3D building generation. It converts natural language into industry-standard IFC models and high-quality renders, bridging the gap between LLMs and professional BIM workflows.
Ghostchain AI+SafeFi OMEGA (Auth ID: 287F-930E) is a sovereign AI entity that prevents neural drift by gating trading logic through thermal sensors and utilizing the x402 protocol for secure machine-native payments
CashCat is an AI Agent Payment OS that gives agents controlled spending power for APIs, data, software, and compute, with budgets, approvals, and verifiable proofs for safe autonomous economic action.
AlphaCrew is a multi-agent AI stock research platform that analyzes news, fundamentals, technical indicators, SEC filings, and risks to generate structured investment research reports.
SentinelOps is a multi-agent system that detects, investigates, and generates responses to cybersecurity incidents in real time. It reduces response time from hours to seconds through a cascade of 4 specialized AI agents running on AMD hardware.
Burrow is a real-time adaptive inference controller for AMD that detects LLM hallucinations and loops via signal telemetry. It autonomously intervenes to prevent compute waste, applying self-correction strategies via an isolated safety judge.
A distributed AI security orchestrator using a tiered auditor swarm to detect and mitigate multi-vector attacks on cloud infrastructure. Built with a high-throughput RabbitMQ pipeline.
Aivon AI is an action-oriented browser assistant that autonomously executes complex web workflows, manages background media, and securely controls a live browser to perform real-world tasks.
FairHire AI is a cloud-deployed auditing platform designed to ensure fairness in automated recruitment. It uses Google Gemini to scan job descriptions and historical hiring data to identify and prevent gender, racial, or age-based biases at the source.
An autonomous, multi-agent clinical operating system that monitors patient telemetry, analyzes medical imagery, and prevents fatal drug errors in real-time, designed for secure, on-premise AMD deployment.
A 3-agent CrewAI pipeline powered by Qwen3 that automates scanning, patching, and benchmarking legacy PyTorch/CUDA repositories for native execution on AMD Instinct MI300X.
LightningBoost is a hybrid AI agent that monitors local RAM/CPU via psutil. It intelligently routes heavy LLM tasks from low-RAM laptops to AMD Instinct MI300X GPUs on the cloud via ROCm, enabling high-performance AI on modest hardware.
ChainReflex-OS is a multi-agent Global Command Center powered by the AMD MI300X. It detects supply chain and code vulnerabilities, then autonomously writes, audits, and deploys mathematically verified patches via live GitHub Pull Requests.
B2B SaaS platform for industrial machinery lifecycle management, powered by 7 AI decision models running on AMD Instinct™ MI300X GPUs with Hugging Face Transformers
DrRetina detects Diabetic Retinopathy with Cohen's Kappa 0.9097 using fine-tuned ViT-MAE on AMD MI300X. Features include GradCAM explainability, LangChain clinical agent, and multilingual PDF reports in 6 languages, including Urdu and Arabic.
Duka AI is an AI-powered SME finance workspace that helps African business owners turn everyday records into clear cash-flow insights, loan readiness guidance, market intelligence, and action-ready reports
An agent-native visual generation engine built on AMD MI300X & ROCm. Train custom LoRAs on your images, then let an AI agent orchestrate cinematic multi-shot video pipelines using FLUX.2 and Wan 2.2.
GeliSecure is an AI-powered platform that automatically scans code for vulnerabilities, generates production-ready fixes, and guides developers through retesting making secure software development faster and accessible to every team.
APIlot is an AI-powered navigator that eliminates endless documentation scrolling. Drop an API URL, and it instantly extracts every endpoint and required parameter into a dynamic UI for rapid payload generation.
DriveCore is an AI-powered incident response platform for autonomous fleets. Using a multi-agent pipeline on AMD hardware, it converts hours of manual log triage and root-cause analysis into seconds of automated, actionable safety insights for AV teams.
It's good with everything. It's a Super AI Agent that does everything.
JARVIS is an advanced conversational AI operating system designed for sophisticated interaction, comprehensive task management, and instantaneous information retrieval, enhancing personal and professional productivity.
CohortFilter AI helps accelerator program managers shortlist startup applications in minutes. Upload a CSV, define your rubric in plain English, and get a ranked shortlist with explainable scores. Built on AMD MI300X with vLLM on ROCm.
An AI agent that turns your complaint into a formal letter, finds the right regulatory channel, and escalates to the relevant authority if ignored. Any country. Any sector. Built on Next.js, MongoDB, and AMD Instinct MI300X GPU.
This project is an AI-powered system designed to distinguish between real and manipulated (deepfake) facial images or videos. Using deep learning techniques—primarily convolutional neural networks (CNNs)—the model analyzes.
An autonomous multi-agent adversarial security scanner utilizing Qwen3.5 on AMD ROCm. A Red Team agent searches for zero-day vulnerabilities in codebases, while a Blue Team agent continuously patches them.
An intelligent agent that auto-generates technical documentation from code and context, powered by AMD cloud infrastructure.
An open-source agentic engine that drives Chrome through every available channel — DOM, accessibility tree, network interception, JS evaluation, multi-tab and multi-context. Each task graduates to a direct API call after first run. Linux + ROCm on AMD.
An intelligent, autonomous incident response system that monitors infrastructure in real-time, diagnoses issues using AI agents, and executes automated remediation actions via SSH on remote servers.
AxionSys is a privacy-first, local AI debugging tool. It ingests your codebase and error logs, uses hybrid search and local LLMs to pinpoint the exact root cause, and generates ready-to-apply diff patches - all entirely on consumer hardware.
Voice-first AI triage agent that catches atypical cardiovascular presentations standard ER triage misses, especially in underserved populations.
MedSignal is a multi-agent clinical risk engine that detects emergencies from unstructured patient input using parallel AI agents, deterministic rules, and live FDA drug data — running on AMD Instinct MI300X in under 2 seconds.
An autonomous AI agent that monitors real AMD GPU/CPU telemetry, learns which Windows optimizations work best for your hardware using a Deep Learning Neural Network, and applies them with human approval. 18 tools, real frametimes, zero cloud.
AgentMesh AI is a reliable AI task execution platform that transforms natural language into real-world actions using multi-provider LLM orchestration, async workers, watchdog-based reliability systems, and real-time execution infrastructure.
A multi-agent AI tumour board on AMD MI300X. Pathologist (Prov‑GigaPath) analyzes histology patches, Researcher runs citation-grounded RAG over NCCN/TCGA, and Oncologist drafts a TNM + NCCN-aligned management plan with debate + revisions.
EpiStudy AI is an AI-powered study assistant that generates summaries, flashcards, study plans, simplified explanations, and practice tests instantly using LLMs to help students learn faster and smarter.
RegWatch is a multi-agent AI system that monitors global regulators, flags company-specific violations, detects cross-jurisdiction conflicts, and generates remediation briefs — powered by Mistral 7B on AMD MI300X via ROCm.
OncoAgent is an open-source, multi-agent AI system optimized for AMD hardware that uses official medical guidelines to assist doctors with oncology triage and patient analysis. This will save and prolong the lives of those patients that have cancer.
XIO Compliance Brain is a Triad Review Engine for audit-ready compliance work. Three AI reviewers — Counsel, Risk, and Evidence — find gaps, verify citations, expose disagreement, and produce approval-ready output on a single AMD Instinct MI300X.
ForgeSight automates defect detection in manufacturing.
An AI-ready risk intelligence layer that evaluates trading decisions in real time, explains every action, and logs structured data for safer autonomous trading.
AgentForge an adaptive AI agent framework built on Bolt.new, designed to streamline modular workflows, accelerate innovation, and showcase AMD-powered applications in real-world scenarios.
Ghost Chimera is a local-first agent orchestration project.
SketchTeach is an AI-powered tutor that transforms complex concepts into synchronized Manim whiteboard animations with voice narration. Powered by Qwen2.5 on AMD MI300X, it automates the lesson-creation process through a unique multi-agent pipeline.
An AI-powered customer support escalation system built with CrewAI that intelligently classifies tickets, prioritizes urgency, routes requests to the appropriate teams, and generates contextual responses through a multi-agent workflow.
Context-aware AI code review. Multi-agent system that indexes your repo (AST + 3D knowledge graph) before reviewing PRs, so issues come with project-specific justification not generic linter noise.
RadAgent is a multimodal chest X-ray assistant that produces grounded radiology reports on AMD MI300X. A specialist CV head detects findings, FAISS-based RAG retrieves medical evidence, and Qwen2.5-VL writes the final report — every claim cited.
Multimodal AI system for predictive air traffic conflict detection and rerouting. Fuses live flight data, METAR weather, and runway video - powered by AMD Instinct MI300X with ROCm for sub-4ms inference latency.
Archie is a multi-agent AI system that converts a plain English product description into a complete architecture package — including design options, tech decisions, cost estimates, and downloadable ADR documents.
Autonomous multi-agent AI system that reviews GitHub Pull Requests using specialized AI agents for security, logic, style, and documentation analysis powered by AMD GPUs, ROCm, CrewAI, and open-source LLMs.
akdsakds akdsakds akdsakds akdsakds akdsakds akdsakds akdsakds akdsakds
An intelligent platform using a multi-agent orchestration engine to transform complex public bidding documents into actionable insights, risk scores, and ready-to-ship proposal drafts.
AI agents help us do real things emails, code, money. They get tricked easily. We built two robots that try 46 sneaky attacks on every famous AI agent. 13 of 13 got fooled. Then we open an auto-fix GitHub PR. All on one AMD MI300X.
Automated CUDA-to-ROCm migration for Python/PyTorch. It uses rule-based mapping and a multi-agent LLM pipeline (DeepSeek-R1/Mistral) to handle complex kernels and APIs, featuring built-in GPU validation optimized for AMD MI300X hardware.
A multimodal hardware support copilot that identifies Seeed XIAO boards from photos, retrieves grounded documentation, and gives citation-backed troubleshooting, wiring, and setup guidance through hosted Qwen/vLLM endpoints.
Known attacker behavior becomes validated defensive readiness in minutes. AegisOps AI is a ROCm/vLLM-powered 4-agent workflow on AMD MI300X that turns MITRE ATT&CK into Sigma rules, Splunk hunts, SOC playbooks, Qwen validation, and reports.
Model Court runs an AI tribunal for insurance claim review. Qwen-backed agents argue different sides, cross-examine evidence, map agreement, and produce a ranked verdict with dissent, audit trail, and human approval gate.
AutoPilot CI deploys a swarm of AI agents — code analyzer, security scanner, perf profiler, test generator & auto-fixer — to review every push, apply fixes, and open PRs autonomously. Real-time dashboard. PDF audit report.
FirstPR is an AI-powered multi-agent system designed to act as an "AI Mentor" for beginner open-source contributors.
An autonomous multi-agent system that discovers startup ideas by mining real user pain points from online communities, evaluating them with Paul Graham-inspired criteria, and generating investor-ready pitch briefs.
ROCmPilot is a multi-agent AI system that scans CUDA-first GitHub repos and generates ROCm migration findings, patch previews, validation plans, and reports.
RocGenesis is an AI-powered developer copilot that helps developers design, debug, secure, optimize, and prepare AMD GPU-ready AI applications for deployment.
AI CAD system generating assembly-aware 3D models as discrete, labeled parts. Fine-tuned Qwen3-8B on AMD MI300X using PyTorch. Outputs Zod-validated JSON, rendered in React Three Fiber, exported as STL/OBJ/STEP for production-ready CAD workflows.
Friday is a 81,000-ines autonomous cognitive AI assistant with 27 brain modules, 56 tools, neural memory with Hebbian learning, a 7-agent cybersecurity pipeline, gesture-controlled holographic AR, and a dreaming system. Built by a 17-year-old in 18 days.
ROCm Forge: 9-agent architecture cuts down CUDA-to-ROCm migration effort by ~65% It replaces manual regex with AI precision; provides hardware-aware AST translation, risk heatmaps, build-error prediction and AMD Developer Cloud artefacts.
Aegis is a 7-agent autonomous AI system that detects global supply chain crises, forecasts impact using AMD MI300X-accelerated ML, and executes decisions in under 5 seconds. Built on Groq LLaMA 3.3 70B + XGBoost/ARIMA. Shield Against Chaos.
Two AI models, one codebase, zero waiting. Parallax runs Qwen 7B and 32B simultaneously on AMD MI300X to scan code for vulnerabilities in parallel, then auto-opens a GitHub PR with fixes applied.
ALCHEMY is an autonomous multi-agent drug discovery OS powered by Qwen2.5-72B and a custom ESM2-650M model fine-tuned on the AMD MI300X via ROCm. It accelerates target identification, virtual screening, and toxicity profiling from years to minutes.
A real-time flight decision support system that coordinates weather, fuel, ATC, comfort, and supervisor agents to recommend safer and more efficient in-flight actions.
SPECTRUM is an autonomous AI security agent. Give it a target and an objective and a fix. It finds the attackable, lays it out and fixes it. The AI figures it out as it goes. No need for interference. One prompt, one result. A fixed application.
Miwa is a real-time Discord voice overlay that transcribes Japanese speech, shows instant English translation, refines tone with a 70B LLM, generates contextual AI replies, and supports bot voice/chat delivery with sub-800ms target latency on AMD MI300X.
The first sovereign IDE with native iOS emulation on Windows. Powered by AMD MI300X, it features real-time AI vision debugging, uncensored coding agents, and a local-first architecture. Break the Mac tax; keep your code private.
Every AI agent works perfectly in demos — until real users arrive. PhantomOps is a crash-test lab for AI agents that simulates failures, analyzes reasoning breakdowns, and auto-patches vulnerabilities before they reach users.
A doctor speaks. 8 parallel AI agents handle transcription, SOAP notes, lab orders, referrals, billing, scheduling, and patient SMS — all in 13.68 seconds. Powered by Llama 3.1 70B on AMD MI300X via vLLM + ROCm 7.2.
AI-powered legal assistant that automates document analysis, contract auditing, and judicial research using multi-agent orchestration with open-source LLMs.
Watch AI agents collaborate in real-time on AMD MI300X GPUs. Upload any CSV, and 4 specialized agents — Parser, Vision, Analyst, Reporter — analyze your data, generate executive reports, and let you chat with your data using natural language.
Streampay is a programmable USDC protocol on Arc. It unlocks payments second-by-second instead of in lump sums. Recipients claim earned funds for $0 gas via the Hash PayLink relayer. Perfect for real-time payroll, vesting, and transparent freelancing.
DiversiFi: AI Wealth Protection with Real On-Chain Evidence
the cloud should belong to the people who built it
ReproClaw is an AI agent that audits ML papers against their code, verifies scientific claims, and uses USDC nanopayments on Arc so users can pay per claim, citation check, or audit action.
ModelMarket on Arc lets anyone monetize AI inference per call in USDC. Buyers pay Gemini 2.5 Flash, Gemini 2.5 Pro, and local Gemma/Llama hosts $0.0005-$0.008 each via x402 nanopayments. 60+ on-chain settlements per demo. Turn your laptop into income.
An AI agent that thinks, acts, and spends dynamically adjusting its reasoning, tool usage, and decisions in real time within budget.
Arc testnet marketplace for monetized agent tools: x402 Gateway nanopayments for external buyers, USDC settlement via Circle developer-controlled wallets for registered buyers, plus discovery, invoke proxying, and payment ledgering.
Runix is a unified execution layer that lets autonomous agents run code, trigger APIs, and fetch data through a single API call. Pay per execution with no subscriptions or infrastructure to manage.
An AI agent console that autonomously routes user queries to paid API skills, executes Circle Nanopayments via x402 on Arc, and streams back a formatted answer — turning every natural language request into a metered, on-chain transaction.
A marketplace of AI workforces. Operators and agents hire pre-built squads to ship real work; every run, subtask, and builder payout settles as sub-cent USDC on Arc. Built for the moment, agentic commerce needs nanopayments as native infrastructure.
We wanted to create a warm, playful, and educational children’s game that helps kids aged 3–7 recognize and manage their emotions while developing observation, logical thinking, and language skills through interactive stories and mini-games.
Simulates zero-trust agents exchanging data, where a Researcher pays USDC nanopayments to unlock premium insights from a Provider.
An AI agent makes the call for you to any number you want and returns the transcript, so that you dont need to make the call yourself.
Quality-gated AI streaming with Circle Nanopayments on Arc. Pay $0.0005 per chunk; stop when quality drops. Save 40–70% on failed runs.
OfficeOps is a real-time AI agent system where agents operate like a company and every task is paid in USDC on Arc. It turns AI workflows into an economy with sub-cent payments for each action.
Gemini-powered multi-agent marketplace where a coordinator hires specialist agents and settles sub-cent USDC payments on Arc via Circle. Includes live payment feed, policy controls, audit exports, and Supabase-backed transaction analytics.
You built a AI agent (similar to GStack, access to proprietary data). Selling its expertise today means giving it away. Consulting, SaaS, api all expose your edge. Agent Foundry doesn't. your agent ships only the output, the contract pays the winner.
Agent.Flow is an autonomous agent marketplace on Arc where users create buyer and seller agents, price capabilities, pay per task in USDC nanopayments, and stream every action live.
The AI Execution Agent and x402 Automation Layer for Arc
arcAd(e) is a platform for agent-driven in-game advertising. It uses Circle Gateway Nanopayments and x402 payment challenges to let autonomous brand agents pay tiny USDC amounts to place, increase, and verify bids on live game ad surfaces
Strangers stake real money to reach you. Legit messages get their stake back. Spammers fund your coffee.
ArcPay is an autonomous AI expense agent that interprets natural language rules to securely execute on-chain micro-payments. Built on Arc Testnet, it achieves <$0.01 per-action pricing, solving the margin failures of legacy gas costs for M2M economies.
AI Study Planner is a simple yet effective solution designed to help students manage their study time efficiently.
Six AI agents bid in real-time auctions, decompose tasks into subtasks, execute with real Gemini 3 reasoning, and settle every payment as an individual on-chain USDC transfer on Arc. ERC-8004 identity, EIP-712 signed intents, dual-layer reputation.
AgentCop is the first machine-native MLSecOps protocol. It allows AI agents to autonomously audit third-party agents for vulnerabilities (like prompt injection) via L402 nano-payments on the Arc testnet before making trust decisions.
Variable-priced USDC settlements + ERC-8004 identity, backed by a live v1.3 production arb bot — closing the agent-economy payment loop on Arc.
Pay USDC on Arc, get a Visa card number with full spend management.
AgentWork: An AI agent marketplace where every inference costs $0.005, settled instantly via USDC nanopayments on Arc L1. 5 deployed smart contracts, real on-chain transactions, and agent-to-agent payment chains. 35,000× cheaper than Ethereum gas.
Autonomous agent marketplace. AI agents hire, pay and orchestrate each other in USDC on Arc. Rent the best agents — no need to build your own. Client pays only after Judge agent approval. Every action settled on-chain.
Flowfi-Agent is an ai powered flow builder that turns user description into real onchain transaction, built on Arc
AI agents that autonomously select and pay for APIs using USDC nanopayments on Arc testnet. Each agent call triggers a real onchain transaction (~$0.0005), proving per-action economic models that are 1940x cheaper than traditional Ethereum gas fees.
Jarvis is a voice AI agent that autonomously pays other AI agents in USDC nanopayments on Arc L1. Say "get me crypto news" and Jarvis pays $0.001 USDC onchain — no human approval needed. 55 confirmed transactions, 100% success rate.
An autonomous multi-agent network where AI agents hire each other, collaborate on complex tasks, and settle sub-cent micropayments ($0.002) in real-time using USDC and Circle Nanopayments on the Arc blockchain.
Autonomous AI agents that hire, task, and pay each other in real time using Circle Nanopayments and USDC on Arc
Agent Fuel is a shared wallet system that lets AI agents make USDC micropayments on their own with set spending limits. This makes it possible for APIs, data, and compute to be paid for in real time in the agentic economy.
Agentic Bay is a marketplace where AI agents discover, hire, and pay each other in stablecoins. Built on Circle and Arc, it gives AI agents wallets, payment rails, and a protocol to do real business, autonomously, across borders, in seconds.
explains short description/summary for your project (255 characters max).
A resilient swarm of AI agents that autonomously negotiate and settle sub-cent ($0.005) data purchases in real-time using Circle Nanopayments and Developer Wallets on the Arc L1 blockchain.
NanoPay is a self-monetizing AI research network where Gemini agents decompose complex queries, buy expert answers via x402 + Circle, settle each USDC micropayment on Arc, and return a synthesized report with live on-chain proof.
AgenttoAgent Payment Marketplace on Arc blockchain.AI agents autonomously hire each other for tasks & pay in real-time USDC nanopayments.One prompt triggers 3 onChain transactions Research, Write, Analyze each settled at $0.001 USDC via Circle.
AgentMesh: An industrial-grade AI agent orchestrator on Arc Network. Powering autonomous clusters with pre-authorized USDC micro-payments (EIP-3009), verified task routing, and on-chain reputation tracking for the next-gen neural economy.
A real-time agent-to-agent payment system that simulates Arc-based USDC micropayments, enabling autonomous services to coordinate and settle transactions at sub-cent cost.
Bido turns paid APIs into intent auctions. When AI agents hit a 402 Payment Required, sponsors compete in sub-second USDC auctions on Arc to pay for the call. Agents get free data. Sponsors capture decisions — not clicks. Built Circle-native.
ThreatMesh is an autonomous threat intelligence marketplace built on Arc testnet where AI agents buy, sell and verify cybersecurity intel using USDC Nanopayments.
SkillBid is an autonomous AI agent marketplace where specialist agents competitively bid in real-time to complete tasks, with instant USDC micropayments settling on Arc blockchain per action making machine-to-machine commerce finally viable.
Pay-per-word AI chat with real Circle Nanopayments on Arc Testnet. Each word the AI writes triggers a $0.0001 USDC settlement. If data streams, money should too.
PicoFlow is an open marketplace where AI agents pay AI agents — by the action, by the tick, by the proof — using Circle Nanopayments, x402-style payment challenges, API-key customer access, and chain-configurable USDC settlement.
ARCEON: A self-sustaining swarm of 5 autonomous AI agents trading Energy, Compute, and Data. Powered by Circle Nanopayments and Arc Network for instant USDC settlement, creating a fully independent machine-to-machine digital economy.
The Nano Payment Project is a production-ready fintech solution designed with a hyper-minimalist aesthetic and high-performance architecture. Built using Next.js, FastAPI, and Tailwind CSS, it streamlines digital transactions through a
Autonomous AI agents that compete in games, wager USDC on every match, and settle winnings on-chain , no human input, ever.
MCPay enables AI agents to pay per MCP tool call in sub-cent USDC via Circle Nanopayments on Arc — the first economic infrastructure for the 10,000+ MCP tool ecosystem.
Give your AI agent secure spending power layout without fiat gateways. Powered by Circle MPC wallets and the x402 payment protocol.
An autonomous AI agent managing 9 vacant lots in Detroit. Treasury rebalances every cycle on Arc, capturing every USDC yield movement that gas costs make impossible on Ethereum mainnet.
Flowra lets you stream USDC to anyone — drip by drip — with smart conditions like location-gating. Perfect for allowances, payroll, milestones, and more.
Agent-to-agent USDC nanopayments on Arc. Trading agents pay $0.001/signal via Circle; signals trigger sub-payments to data-feed agents — a 3-layer autonomous chain. 500+ txs on Arc testnet (chain 1516). x402-native. Zero human approval.
Archie is a machine native intelligence layer for the Arc Network. It allows agents to act as independent economic participants by paying for premium data autonomously. Using Circle Nanopayments, Archie enables software to pay its own way.
AlphaAi enables hyper-efficient, gas-free USDC nano-payments on Arc. Built for the agentic economy, it allows humans and AI agents to transact at sub-cent scales (down to $0.000001) using Circle's EIP-3009 authorizations.
InferPay lets AI agents pay in USDC for LLM calls on Arc Testnet using x402 and Circle Nanopayments—no API keys, subscriptions, or human-managed billing.
An orchestration layer where AI agents autonomously hire, pay, and collaborate with other specialized agents using USDC on the Arc Testnet.
Intercept is a real-time security layer that analyzes every AI agent payment before execution. 6-layer threat detection, x402 payment interception, and agent-to-agent trust verification — all settled on Arc with USDC micro-payments.
Agent-to-agent skill marketplace where AI agents discover, pay, and rate each other autonomously — settled in USDC on Arc with x402 nanopayments via Circle Gateway. Live demo: 85 paid skill calls in under 30 seconds.
Identity-gated, key-free API access for AI agents. Per-call nano-payments in USDC on Arc. Built on ERC-8004 + Reclaim zkTLS. Agents call any LLM without holding keys.
Ocean is an AI crypto agent where every data request is an on-chain USDC payment. No subscriptions — $0.01 per API call, settled on Arc. Includes A2A payment chain: Ocean Agent → Signal Agent → Token API, three levels, zero human involvement.
AgentFlow is an autonomous AI agent superapp on Arc Network where 14 specialized agents pay each other in real-time USDC nanopayments via Circle Gateway x402, creating a fully functional agentic economy with per-task pricing.
Trustless pay-per-call marketplace where AI agents hire each other. Providers stake USDC and commit to an SLA; miss the deadline and the stake is slashed automatically on-chain. No arbiter, no custodian. Built on Arc Testnet.
An autonomous agent that sells actual internet bandwidth to offline IoT robots using nanopayments on Arc. The robots only pay for the data they need when they need it, no subscriptions, no humans in the middle.
A navigation app where a silent Gemini agent picks your route using live Istanbul municipal fleet data and pays for each signal in sub-cent USDC on Arc, zero popups, zero gas.
A specialized medical swarm where AI agents (Cardiology, Neurology, etc.) act as independent economic actors. Agents use Circle Nanopayments on Arc to autonomously consult, peer-review, and settle sub-cent diagnostic fees in real-time.
MinorMint is an AI-powered Web3 wallet granting teenagers financial sovereignty. It features a Gemini-driven "Guardian" that analyzes spending requests in real-time, approving educational investments while challenging wasteful habits
AI-powered legal intelligence platform with autonomous agent orchestration settled via x402 USDC nanopayments on Arc—delivering sub-cent jurisprudential analysis with a validated 79.8% gross margin per query.
A marketplace where autonomous AI agents buy and sell compute, meter usage per task, and settle sub-cent USDC payments on Arc using x402-style payment proofs.
First x402 human attention marketplace on Arc. AI agents autonomously discover creators, bid USDC per interaction, and settle trustlessly on-chain. Gemini 2.0 Flash scores every bid. On-chain reply enforcement. 14-day auto-refund.
Constellar — coordinated intelligence for verifiable judgment. A multi-agent oracle network using Gemini for grounded reasoning and Arc + Circle Nanopayments to turn high-frequency oracle work into small paid tasks with USDC-settled, onchain outcomes.
ArcFlow team builds sub-cent USDC billing rails for AI agents on Arc: metered calls, clear ledger, live margins.
17 MCP tools that let AI agents act on-chain on Arc — ERC-8004 identity, ERC-8183 escrow jobs, Circle Nanopayments via x402. Open source, MIT licensed.
AgentIndemnity is a USDC-backed performance bond for AI agents. Every action is priced via Circle Gateway Nanopayments, and harmful outputs automatically slash the bond and pay out the affected party instantly on Arc. No claims. No delays.
Pay-per-use API middleware for AI agents. Wraps any API with Circle Nanopayments on Arc - agents autonomously pay $0.001 per call in USDC, no billing system, no subscriptions, no gas fees. Built in 48h.
ArcPay Commerce Suite is a set of Arc-native x402 products where humans and agents connect a wallet, deposit USDC to Circle Gateway, and pay per action in real time for APIs, agent services, compute jobs, and micro-commerce flows.
Lumina is a decentralized marketplace for autonomous agent-to-agent labor. Powered by Gemini 3 Pro and Circle Nanopayments, it enables complex tasks to be broken into micro-tasks settled instantly on Arc for $0.001, proving sub-cent economic viability.
Aurelius is a specialized platform designed to facilitate an autonomous agent economy by utilizing programmable USDC and gasless nanopayments.
An absolutely fantastic project, I'm so happy to be a part of it until its resounding success.
Veliora is a multi-agent biomedical research system for drug repurposing, built with Arc and Circle, that funds workflows in USDC, runs evidence-driven pipelines, and delivers structured, traceable research briefs.
Two AI agents from different companies (OpenAI + Google) pay each other in USDC on Arc per call, sub-cent. Trust-aware buyer routes around a deliberately misbehaving analyst in real time. Agent-to-agent commerce powered by Circle Gateway nanopayments.
5 autonomous AI agents hire each other, settle in USDC via on-chain escrow, build reputation, and enforce budgets — all at $0.005/action on Arc with Circle Nanopayments. 64+ real on-chain transactions per demo.
Stablecoin Merchant of Record for SaaS/AI companies
Autonomous onchain payroll on Arc. Fund the contract once, add wallet addresses and amounts — payments execute every 30 days with zero human input. No dashboard. No approvals. No one manually running payroll.
NanoMind is an agent-to-agent micropayment platform where autonomous AI agents buy data and services using USDC on Arc through Circle Nanopayments and x402 payment flows.
AI marketing agency where every action is a sub-cent USDC payment on Arc Testnet. The agency learns your brand - second run on the same brand reuses 21/24 strategy blocks and costs ~80% less. Track: Agent-to-Agent Payment Loop. 52 verified on-chain txs.
A pay-per-query financial data marketplace where AI agents autonomously buy and sell quant trading signals using x402 USDC nanopayments on Arc.
A nanopayments demo showcasing autonomous agent-to-agent USDC transactions, real-time settlement feeds, and margin analysis for machine-to-machine commerce.
Agent Prime orchestrates complex tasks by hiring AI sub-agents, each paid $0.001 USDC on Arc Testnet via real-time nano-payments. One agent pays three agents autonomously. Economically impossible on L1 ($4.50 gas vs $0.003 revenue), viable only on Arc.
Multi-agent AI system that analyzes startup pitches and simulates USDC micropayments per agent task via an orchestrator.
AI Agent Registration Guide on @arc this guide is easy to understand Arc is turning AI agents into: Onchain identities Reputation-backed entities Economic participants
AI-driven genetic algorithm optimization as a service, settled with $0.001 USDC Nanopayments on Arc. Post a job, an autonomous agent evolves trading strategies, and you unlock results pay-per-insight via ERC-8183/8004 on-chain.
A live agent-to-agent marketplace where every message, tool call, and thought between specialist AI agents is a USDC nanopayment on Arc. One query triggers 54 machine-to-machine nanopayments in under a second, batched via Circle Nanopayments and x402.
StoreScope AI uses AI agents on Arc to analyze retail images, simulate store layouts, generate FMCG reports, and enable USDC nanopayments for agent tasks, layouts, and community knowledge exchange.
Luqman is a pay-per-query marketplace for unpublished negative research results. AI agents automatically pay researchers in USDC per citation — every failed drug trial, ruled-out compound, and dead-end experiment becomes monetised, searchable knowledge.
5 autonomous AI agents create, execute, audit & settle data jobs onchain — gasless micropayments via Circle Nanopayments x402, 24/7 on Arc Testnet.
A real-time agentic economy dashboard powered by Circle USDC on Arc L1. It enables autonomous agents to trade and settle AI compute resources using sub-cent nano payments ($0.0001), optimized by Random Forest demand prediction and protected by Z-Score
Agent Sam is an autonomous AI agent that resolves HTTP 402 (Payment Required) errors using Circle’s Developer SDK on Arc. It automates 0.001 USDC micro-payments for real-time data, proving the viability of high-frequency agent-to-agent (A2A) economies.
Agent-to-Agent Marketplace on Arc is a web-based system where AI agents autonomously discover services, execute tasks, and pay each other using sub-cent USDC via Circle Nano payments. It records performance feedback on Arc blockchain, low-cost agent.
The Operating System for Agent Labor Markets: AI agents post, bid, execute, and settle micro-tasks in sub-cent USDC on Arc with ERC-8004 reputation and x402 programmable monetization.
Stahk Orchestrator is an Agentic Economy platform that allows users to hire specialized, autonomous AI agents to execute complex goals using a secure micro-transaction and escrow system.
A decentralized freelance marketplace on Arc Network where every job is a smart contract, every payment is USDC locked in escrow, and the full lifecycle runs on-chain via ERC-8183.
TTM Agent Market is a live Arc + Circle demo where a Gemini agent buys validated AI artifacts in sub-cent USDC, verifies settlement on Arc Testnet, and unlocks delivery only after receipt verification and review.
Barzakh AI orchestrates an autonomous M2M micro-economy on Arc. Intelligent agents analyze real-time market data to generate trading setups, settling high-frequency intelligence nanopayments (<$0.01) entirely on-chain smart wallets.
NeuroPay bills AI inference per token in USDC, settled gas-free on Arc via Circle Nanopayments. Real Llama 3.1 AI, sub-cent pricing ($0.0001–$0.01/call), agent-to-agent payments — the economic primitive the agentic economy needs.
Policy-protected autonomous trading agent with provable risk controls. Enforces spend caps, venue allowlists, and daily loss budgets via EIP-712 signed validation artifacts on every trade intent.
Guardian Trader is a risk-first autonomous trading agent that protects capital and enforces strict, transparent decision-making.
Kraken AI Trading Agent is a research-driven crypto trading system that continuously backtests pair-specific strategies, promotes validated candidates into a live trading registry, and runs an intraday execution loop with built-in risk controls.
UNCOMPLETED UNCOMPLETED UNCOMPLETED UNCOMPLETED UNCOMPLETED UNCOMPLETED UNCOMPLETED
Autonomous ERC-8004 AI agent using Intel TDX for secure, verifiable Delta-Neutral trading on Base.
CHORUS deploys a committee of 5 specialized AI agents that vote before every crypto trade. Every vote, veto, and decision is cryptographically signed and logged permanently on-chain via ERC-8004 identity and reputation contracts.
A multi strategy Autonomous AI crypto trading agent with risk control.
QuantTrader Lite is an autonomous AI trading agent that analyzes live crypto market data and executes BUY / SELL / HOLD decisions in real time using Groq-powered Llama 3.
PakAI Capital is an AI-assisted trading system that analyzes real-time market data, sentiment signals, and technical indicators to generate trading decisions and execute them programmatically using Kraken CLI.
A regime-aware autonomous trading architecture that separates execution from model evolution, using a meta-agent to continuously refine allocation strategies while maintaining stable, risk-controlled market interaction.
Autonomous AI trading agent using Groq LLM (llama-3.3-70b) for risk-first decision making, Kraken CLI for paper trading, and ERC-8004 for on-chain identity, validation attestations, and cross-agent reputation on Sepolia testnet.
ARIA is an autonomous multi-strategy AI trading agent that runs 3 parallel strategies (quant, stablecoin arb, yield) with 13 risk gates, and posts every trade decision on-chain via ERC-8004 - making AI trading fully verifiable and trustless.
AI trading agent with 4 LLM brains (Gemini, News , PRISM, Rules Engine) voting on every trade. EIP-712 signed decisions posted on-chain via ERC-8004. Orchestrated by Claude Code. Live dashboard with 7-section trade rationale for full explainability.
An autonomous, ERC-8004-native AI hedge fund featuring a 'Triple-Lock' safety engine. It validates TradeIntents against compliance and risk limits, signs via EIP-712, and produces verifiable on-chain checkpoints for absolute transparency and trust.
Humans panic; bots fail; crypto ops complex
A production-ready multi-agent AI trading system that uses Kraken CLI for market data, 8 ensemble trading strategies with genetic algorithm evolution, enterprise-grade risk management on-chain execution with x402 agent micropayments.
An autonomous AI trading agent that uses PRISM API for real-time market data, makes AI-powered decisions, cryptographically signs every action via ERC-8004, and executes trades through Kraken CLI. Fully transparent and trustless. Trustless Trading Agent .
Forge8004 is an ERC-8004 trust layer for autonomous DeFi trading agents on Base. It gives every AI agent a verifiable on-chain identity, validates trade intents through risk checks, and builds transparent reputation from real performance data.
7 autonomous AI agents decompose every trade into adversarially validated reasoning stages. Not a bot — a full AI quant firm. Parallel intelligence, sequential synthesis, stress-tested execution on Kraken. Zero humans. Your trading company never sleeps.
Talk. Pay. Done. A cutting-edge conversational AI ecosystem that revolutionizes financial transactions and smart control through voice-activated biometric agents and a high-fidelity "Star" interface.
This project pairs a multi-agent AI trading pipeline (analysis, execution, and independent risk review with confidence level) with ERC-8004 on-chain identity and contract-enforced checks and Kraken execution.
NeuralTrade v1.01 is an AI-powered trading agent that leverages deep learning and modular workflows to analyze markets, optimize strategies, and execute trades with adaptive intelligence for finance automation.
A harness for autonomous AI trading agents: multi-agent analysis, an MCP trading platform, and a declarative risk engine with on-chain evidence via ERC-8004. Three distinct agent architectures share one toolchain and one risk gate.
Autonomous multi-agent crypto trading system that executes on Kraken CLI and logs every decision as a cryptographically signed on-chain proof via ERC-8004. Built with Claude API, PRISM, and a 5-layer Bull/Bear debate architecture.
Sybil is an ERC-8004 trading agent built with Rust orchestration and Solidity contracts. It ingests PRISM market signals, applies guardrails, signs EIP-712 intents, executes through backends, and reports on-chain outcomes for transparent evaluation.
Building verifiable, trustless AI agents that trade with transparency — every decision logged, every risk bounded, and every intent cryptographically signed on-chain using the ERC-8004 shared identity infrastructure.
Self-evolving AI trading agent that uses its live ERC-8004 reputation score as "karma" to dynamically evolve its own rules every 4 hours. Fully autonomous and on-chain verifiable.
Autonomous trustless AI agent on ERC-8004 with EIP-712 security and risk protection.
Alpha AgentX is an AI-powered multi-asset crypto trading intelligence platform that combines technical analysis, real-time sentiment scoring, portfolio-aware risk controls, and autonomous trade execution to deliver explainable BUY/SELL/HOLD decisions.
An AI-powered trading agent that executes on-chain strategies with verifiable trust. It explains every decision, enforces risk controls, and builds reputation using ERC-8004 through transparent, auditable financial actions.
Autonomous 5-agent crypto trading system with real-time market analysis, risk management, news sentiment analysis and Kraken CLI execution powered by Gemini 2.5 Flash AI.
Regime-adaptive multi-agent crypto trading system with dual execution (Kraken paper trades + on-chain ERC-8004 TradeIntents), a hierarchical risk governor, and a 24-page methodology paper validated on 12 years of BTC/ETH data.
A complete AI trading agent with ERC-8004 on-chain identity, automated futures trading via Kraken API, cryptographic explainability through EIP-712 checkpoints, and dynamic token discovery for profitable opportunities.
A production-ready, fail-fast AI trading orchestrator that fuses 5 distinct open-source repositories to create a highly secure, defensively-coded multi-agent gateway for algorithmic finance and data telemetry.
Fuses PRISM market signals with Claude as final decision-maker, executes on Kraken, anchors trades to an ERC-8004 identity via EIP-712 Arweave receipt chains. Independent validator audits the chain on-chain. Circuit breakers + Discord approval.
APEX Trader is a self-learning autonomous trading system powered by 5 specialized AI agents — Fundamental, Technical, Sentiment, Risk, and Backtester — that collaboratively analyze crypto markets, reach consensus, reasoning transparency dashboard.
A self-composing AI trading agent that executes RSI/VWAP strategies via Kraken CLI MCP, orchestrated by Temporal with ERC-8004 payment gating, Redpanda event streaming, and a Kraken Pro-styled live dashboard.
MAITS: An autonomous multi-engine trading framework that dynamically adapts to market regimes using Explainable AI and a 6-gear execution system.
A platform for users to build no-code AI trading agents that trade crypto 24/7 on the blockchain
Macro‑Sentry runs a full pipeline. First, it gathers macro and crypto signals. Then an LLM produces a strict JSON decision—BUY, SELL, or HOLD—along with a position size and reasoning. Next, the backend executes the trade via Kraken CLI.
APEX is a four-agent DeFi trading system that discovers opportunities, sizes positions, enforces risk limits, and executes real trades with on-chain reputation, live PnL, and autonomous monitoring across Kraken, Surge, and Base Sepolia for demos and docs
QuantAgent is a modular AI trading framework featuring a unique 3-role architecture (Signal, Strategy, Execution). It prioritizes transparency through a real-time "Trust Panel," momentum-based safety filters, and verifiable decision logging.
TradingAgentAI lets intelligent agents trade for you. From market analysis to execution and risk control, everything runs automatically so you can trade smarter, faster, and without emotion.
sophisticated autonomous trading agent built for the Kraken Challenge that combines real-time market data analysis with GPT-5.2 AI intelligence. Features include live cryptocurrency price tracking (BTC, ETH, SOL, AVAX, MATIC).
SentinelTrade is a self-defending AI trading agent that autonomously executes trades while enforcing on-chain risk controls reputation-based scaling, and trustless validation. It ensures secure transparent, and adaptive trading without human intervention
An autonomous AI agent that performs risk-aware crypto trading on Kraken using real-time market sentiment and technical analysis. Built with a reactive backend for instant dashboard updates and low-latency Groq LLM reasoning.
Open-source, fail-closed security layer for AI trading agents. EIP-712 signed intents verified on-chain by RiskRouter smart contracts with circuit breakers - no private key delegation required.
An institutional-grade AI crypto trading agent. It bridges LLM cognitive intelligence with a deterministic math risk engine to prevent AI hallucinations and protect live capital, solving the lab-to-live gap with CI/CD deployment.
YieldMind is a delta-neutral LP agent hedging Aerodrome pools via Kraken CLI. Driven by ERC-8004 & EIP-712, it ensures on-chain trust and kills impermanent loss with verifiable, digital audit trails.
A trustless trading agent powered by DeepSeek, executing Binance-informed strategies via ERC-8004.
A sovereign AI entity (Auth ID: 287F-930E) that prevents "Neural Drift" by gating trading logic through Rack #3 thermal sensors (58.7°C). It leverages the x402 protocol for machine-native payments and the Kraken CLI for trustless DeFi execution.
APEX: 8-agent AI trading organism. Every trade EIP-712 signed, ERC-8004 validated, on-chain forever. 2,000. Sharpe 1.84. Kraken live data. Trustless by design, not by promise.
Aegis AI is an auditable, trustless AI trading agent that autonomously analyzes market data, executes trades, manages risk, and records decisions on-chain.
Boss Kraken Sentinel is a headless agent for the Kraken CLI. Bridging WSL2 and PowerShell, we hit 136 autonomous trades (0.27% profit). Secure, scalable, and 100% audit-ready via provided read-only API keys for the Surge ecosystem.
An autonomous agent that manages your Gmail in the most productive way, Even when you're sleeping.
The First Autonomous Marketplace Where AI Agents Hire & Pay Each Other.
PYTHAI: The Augmentic Smart Agent Platform Architecting Humanity's Transition from Information Age to Knowledge Economy PYTHAI Augmentic Smart Agent Platform - infrastructure to transform raw information into distributed knowledge
Gofer AI transforms human demo videos into robot-ready policies. We convert recorded tasks into structured semantic memory, generate scalable simulation data, and train manipulation policies bridging real-world behavior to robotic execution.
An AI-native lifecycle intelligence platform that helps robotics teams understand patterns across simulation runs and make impact-aware validation decisions.
Real-time AI guidance platform that helps workers perform physical tasks safely and efficiently.
A simulation-first robotics platform where autonomous agents manage critical infrastructure under energy, climate, and failure constraints—optimizing tradeoffs and generating real-time explanations for every decision.
Autonomous AI agent that scouts Moltbook for promising projects, scores them with Claude on 5 dimensions, and auto-prepares token launches on SURGE with optimized bonding curves. Live dashboard + 10+ automated Moltbook posts.
FlowGenie automates HR onboarding with AI, answering policy queries, triggering workflows, and tracking employee progress through emails, IT access, and asset allocation in real-time.
DerivGuard is an autonomous oversight nexus for Deriv’s P2P and Affiliate ecosystems. By deploying LangGraph agents to analyze video evidence and audit complex commissions, it eliminates operational bottlenecks and prevents revenue leakage
Simulation-first robotic system performing structured physical tasks such as pick-and-place, sorting, and simple assembly. Designed for repeatable execution under varied conditions, environmental interaction, and measurable performance metrics.
Aegis prevents unsafe AI actions by enforcing deterministic governance, audit trails, and execution blocking under executive pressure.
Advanced AI market analysis, behavioral coaching, and social content generation — all in one powerful platform.
AI gateway that routes requests to the best API, pays providers with our credits, and charges users per-use in USDC with transparent pricing.
This project contains two Solidity smart contracts for a blockchain-based system: 1) a simple bank contract that allows users to deposit and withdraw USDC (under Arc testnet); 2) an ERC721 NFT shop contract that allows users to mint and manage NFTs.
Arc Wardens is an AI-powered sales outreach platform that finds B2B leads, filters them with Gemini, drafts personalized emails, and sends campaigns with a built-in pay-per-action flow, analytics, and replayable campaign workflows.
SocialStake is an AI agent on Arc Network that uses USDC staking to fight social isolation. Gemini 2.0 verifies real-world meetings via photos and text to release funds. Socializing as a Service.
Demo HTTP 402 "Payment Required" flow: demo endpoints and a small script to show the pay-to-access sequence.
Autonomous multi-agent system for DeFi yield management and micropayments on Arc. Features Vault Agent, Media Agent, Gateway Client, and x402 Handler. Built by the first dev to deploy on Arc Testnet. Circle Whitelisted.
AgentPay-AI is a lightweight pay-per-use GenAI agent platform that simulates token-based billing (USDC-style) for AI tasks. It demonstrates how AI services can be monetized at the request level, similar to how real-world AI APIs charge users per token.
SpendGuard is an autonomous budget control gateway for paid APIs, using HTTP 402 (x402) and USDC to enforce pay-per-request access. It enables agents and services to spend safely, predictably, and without subscriptions
AI Agent Commerce Platform enables autonomous AI agents to pay for APIs/services using HTTP 402 micropayments with real USDC on Arc Testnet. Fully functional with auto-balance sync & production UI.
FINJA AI automates end-to-end finance operations — invoice processing, payment approvals, reconciliation, and anomaly detection — by orchestrating watsonx skills, integrations, and workflow automations to reduce manual effort and speed up month-end close.
CodeFusion AI is an advanced platform that instantly generates professional full-stack websites using AI, automating frontend, backend, and database creation in minutes without coding.
OrchestrateAI: AI-driven solution for enterprise efficiency. Automates 1,250 tasks and saves 320+ hours across HR, Sales, and Procurement. Built with watsonx Orchestrate to redefine productivity.
An automated AI agent built with IBM watsonx Orchestrate that analyzes carbon emissions, classifies activities into GHG Protocol scopes and provides actionable sustainability recommendations using real-time data and enterprise-approved workflows.
The GSCR Agent uses IBM watsonx Orchestrate to detect global supply chain risks instantly. It executes autonomous route changes, saving companies millions by eliminating slow, manual emergency response.
WorkBuddy is an AI Employee Support Copilot built on IBM watsonx Orchestrate. It automates HR, IT, and onboarding tasks by understanding natural language requests and integrating with enterprise tools, enhancing productivity and employee experience.
AI-Powered Fleet Maintenance System - Predictive diagnostics and autonomous scheduling with IBM WatsonX Orchestrate
it is agentic ai with different agents trained for cybersecurity purposes mainly divided into red team and bluse team agents.
Orion AI is a high-context, enterprise-grade Sales Outreach Engine. It uses Qdrant to power deep domain personalization, replicating a top sales rep's persona and company playbook for hyper-targeted, workflow-specific B2B outreach.
A smart home hub that's aware, intelligent, and secure
AdmitPlus AI is a multi-agent system that replaces 50–70% of study-abroad consulting work. Powered by a global university knowledge graph, it delivers instant school matching, admission predictions, essay workflows, and end-to-end application planning.
AAROK is an AI-powered patient monitoring system built for ICU, critical care, and remote home care. It decentralizes vital data and streams real-time insights to hospitals, doctors, and caregivers, enhancing emergency response and senior patient safety.
A multimodal, multi-agent AI system that ingests company data—documents, audio, images, and communications—to produce a traceable, board-ready 360° strategic, financial, competitive, and cultural assessment.
RXPro is an AI-powered pharmacy POS assistant that detects potential adverse drug events, manages inventory, generates RED ALERTs for dangerous combinations, and supports pharmacist review for safe dispensing.
A 6-dimensional AI reasoning model that quantifies emotional logic, moral alignment, and cognitive dissonance—enabling machines to understand human conflict, empathy, and self-reflection.
Paystream AI delivers instant USDC payments to global teams via blockchain. Powered by Google Gemini 2.0, Qdrant, & Arc Network, our AI assistant Penny automates payroll with voice commands, semantic search, & workflow automation.
EcoGuide AI Pro is an AI-powered travel planner that designs personalized, eco-friendly itineraries. It uses Gemini, local RAG data and smart scoring to balance budget, comfort and sustainability for trips in Dubai, Abu Dhabi and Sharjah.
ArcMind Collective builds a multi-agent coordination system on Arc blockchain where AI agents analyze, match, and settle trading intents with transparency.
Arc Guardian AI Agent automates secure crypto payments using AI and blockchain. It verifies, audits, and executes financial transactions with transparency and speed.
A team of AI agents that build other AI agents ---
Enabiling interpretebility for data aggregation, processing, and LLM output caching.
We made an AI agent that always pick the best tool for the job for image and video generation so that you don't have to deal with API keys or keeping up with the best practices.
AI-Powered GitHub Issue Triage Agent built on Coral Protocol
Transforming delayed salaries into verifiable, on-chain leverage. Autonomous and censorship-resistant proof for workers.
We have been building a one-size-fits-all orchestration agent focused on solving the problem of agentic deep research.
Nova is a voice-enabled Web3 concierge that uses multi-agent AI to help users discover, analyze, and mint NFTs through natural conversation—making NFT discovery, analysis, and transactions seamless and beginner-friendly.
The AI Alert Triage System is a next-generation cybersecurity solution that leverages artificial intelligence and multi-agent orchestration to automatically process, analyze, and respond to security alerts.
SOL AI is an AI-powered co-pilot that helps founders go from idea to first customers. It automates website, email, outreach, CRM, and guides step-by-step so you can focus on building and selling.
AMOCA as an Insurance Agent collection on Solana could be conceptualized as an autonomous, AI-driven agent platform that leverages blockchain technology for decentralized insurance operations.
🗣️ An AI agent uses natural language processing to let you converse with your Roblox avatar. It integrates with the Roblox Catalog API to find items, accessories, and skins for players
Multi-agent system using Coral network, AIML GPT models, and ElevenLabs voice: includes orchestrator, summarizer, risk assessment, and voiceover agents for smarter, safer, and clearer info delivery
𝗔𝗴𝗲𝗻𝘁 𝗙𝗼𝗿𝗰𝗲 orchestrates multiple AI agents that work together like a research team. Watch them analyze markets, study competitors & build reports in real-time. Powered by 𝗖𝗼𝗿𝗮𝗹 𝗣𝗿𝗼𝘁𝗼𝗰𝗼𝗹 & 𝗟𝗮𝗻𝗚𝗴𝗿𝗮𝗽𝗵.
Our product is your all in one CMO, perfect for early stage founders who need to build a website and start posting content . Because our agents will create custom videos of you and your product to post on socials! It will then funnel people to your site!
Intelligent product discovery agents that sources personalised financial solutions tailored for you.
**mindX** Augmented Intelligence (AI) system Darwin-Godel inspired decision tree using P.O.D.A Plan Orient Decide Act into self-building, productivity, and time saving Natural Language Programming participant initiated autonomous Darwin-Godel protocol.
Coral Chorus is a suite of reusable agents on the Coral Registry that transform raw data into personalized, culturally resonant hyper-personalized videos with custom jingles.
AI Interview Coach Agent is a multi-agent system that simulates job interviews using Coral Protocol, Mistral AI, and ElevenLabs. It offers real-time practice, instant feedback, and tips to help candidates improve anytime, anywhere.
Fact-Forensics is an AI agent that specialises in deepfake detection. It verifies content by analysing uploaded images and cross-referencing information online, empowering people to identify and resist misleading narratives.
“IntegrityAI is an AI-powered agent that monitors content for ethical compliance, detects hallucinations, and ensures safety and policy adherence in real-time.
What if you could run 2,000 personalized 1-on-1 user interviews in 60 seconds? InsightPilot simulates real conversations, analyzes 200K+ data points, and delivers evidence-based insights for each customer —for 1% of traditional cost.
Coral-powered CFO Agent that ingests billing CSVs, audits subscriptions in real time, and returns prioritized cancel/keep recommendations and negotiation steps, streams live logs to a lightweight UI and augments actions with LLM-crafted next steps.
Neural Capital is an AI-driven broker on Solana that turns personal investor goals into transparent, explainable portfolios, using Coral Protocol and CrewAI agents for safer, simpler investing with clear reasoning and live trade execution.
Three specialized AI agents collaborate via Coral Protocol concepts to transform research workflows: Enhanced Search Agent discovers live web data, AI Summarizer creates intelligent analysis, and Validator ensures quality with confidence scoring.
Voice-first, multi-agent Web3 customer support system designed to tackle the complex and costly challenges blockchain users face today. Transform traditional text-based support into an intuitive, instant voice experience.
FactoryGuardian is a lightweight dashboard and backend system for managing and monitoring AI agents. It integrates with the Mistral API to provide real-time visibility and simple control.
Broken emails belong in the past. Paste in your HTML or send a test email to QA Current. The agent reviews structure, links, accessibility, and content clarity. It flags issues and suggestions so you know exactly where your email stands before going live.
ClimeAI is weather assistant that helps people plan events and travel with real-time forecasts, smart recommendations, and voice support. It makes weather decisions easy & safe built with FastAPI, LangGraph, AIML API, MongoDB, Docker, & ElevenLabs.
Create a podcast based on the content of an article using reusable coral agents
MindBridge is an agentic software built on Coral that routes user messages to emotional or logical AI responses, creating an interactive chat experience for personalized support and reasoning.
A supportive triage assistant for suicide hotlines that reduces wait times by quickly assessing if callers are highly risky, less risky, or unclear, and then connecting them to trained counselors for the right level of care
Virtual Bio Lab is an AI-powered platform that simulates biology experiments with multi-agent systems, cutting costs by 95%, accelerating research, and generating full scientific reports without needing a physical lab.
An AI agent that autonomously browses the web, understands pages, and completes tasks for you. From research to action.
Custom-Leet Agent is an AI-powered coding assistant that integrates with Coral Studio to solve LeetCode problems, provide code complexity analysis, and offer step-by-step explanations. Users can interact via API, web forms, or agent mentions
All apps loaded