Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
Enabling PMs to create and dispatch context-aware coding tasks to cloud based Gemini Agents
An agentic AI workspace with voice interaction, live documentation, and Git-style conversation branching. Butler transforms conversations into searchable, evolving knowledge you can revisit, compare, and export.
Vridia is a multi-agent orchestration system with hierarchical reasoning and persistent memory. Specialized agents collaborate autonomously, detect architectural drift, acquire missing knowledge, and accumulate validated decisions across sessions.
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.
Dasalt 360 is a high volume IT company, which buy laptops from USA and sell it from Jimeta, Adamawa State to another place. I built a multi-modal AI Agent to help procurement planning, logistics, sells and operational challenges.
Cloud-Native Gemini CLI Agent Swarm for Software Development by PMs and Engineers
Nebula is a cloud-native, AI-powered coding environment where Gemini agents provision GitHub Codespaces, generate code, and auto-remediate errors — all guarded by enterprise-grade security audit trails via Veea Lobster Trap.
FastEnd Agentic AI is a smart workspace that uses AI agents to help people finish work faster. It analyzes long documents, writes code, and simulates how different AI roles can work together on big projects.
AgentRedTeam is a red-team fuzzer that finds gaps before attackers do.
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.
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.
Gemini Mythos is an autonomous cyber-reasoning pipeline using Gemini models to find, sandbox-verify, and patch vulnerabilities. Agent traffic is hard-proxied through Veea Lobster Trap for 100% mandatory enterprise governance.
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.
Friday is an autonomous AI system with persistent memory, multi-agent orchestration, voice, and tool use. It remembers context across sessions and coordinates 30+ agents to help users think, act, and finish complex tasks.
an autonomous AI integration platform that automatically connects React frontends with FastAPI backends by detecting conflicts and generating adapter code.
An AI-powered visual modernization platform that maps complex codebase architectures and instantly refactors legacy scripts into production-ready, modern code.
VibeCheck scans entire codebases using IBM Bob's full-repo context to detect what no linter can: architectural drift, intent mismatches, semantic duplication, and cascading blast radius - the invisible failures that ship when AI writes 60% of your code.
BobForge is an AI app factory that turns a raw software idea into a complete IBM Bob-ready blueprint, then uses IBM Bob to build, document, test, and track the generated application.
Repo-Insight is a code knowledge graph MCP server that gives IBM Bob surgical precision over any Python codebase — replacing expensive file reads with instant graph queries to find and fix bugs in fewer tokens.
DataSentinel automates GraphQL API integration and typing. It performs dynamic introspection, handles backoff retries, and generates structured Python models, eliminating manual mapping to accelerate Data Science and ML workflows.
An AI-powered SDLC workflow automation tool that uses IBM Bob IDE as the core intelligence engine to transform feature ideas into production-ready code through structured, repeatable processes.
MCP Foundry turns CSV/Excel into interactive AI agents via Streamlit. It uses IBM Bob to forge MCP servers, auto-generate OpenAPI specs, and link any local or cloud LLM without manual backend code.
PHRAXIS turns a spoken developer idea into a production-ready GitHub PR in under 4 minutes. IBM Bob reads the full codebase. IBM Quantum QAOA finds the optimal change path. IBM Watson STT and NLU extract structured intent. Voice to impact, end to end.
Enabling PMs and engineers to spin up contextful Bob agents in the cloud
"Bob Full-Stack Auto-Integrator is a VS Code extension that uses IBM Bob to instantly turn static Figma UIs into functional apps. It auto-generates a Node.js/MongoDB backend and seamlessly wires it to your frontend in seconds."
A unified dashboard orchestrating 8 AI CLI tools (Claude, Gemini, Codex, DeepSeek, Copilot, Kimi, Cline, IBM BOB) with intelligent task division, real-time monitoring, and automatic context sharing for seamless multi-agent development workflows.
Stop wasting 43% of your AI tokens on code rework. AgentIQ is an enterprise governance platform that audits repositories and generates deterministic multi-IDE context blueprints, ensuring AI agents like IBM Bob code flawlessly on the very first try.
PromptShield is a security scanner for AI coding assistant configurations across IBM Bob, Claude Code, and Cursor.
OpenLook gives coding agents visual unit tests: they record browser sessions, send the video to Gemini, get pass/fail UX verdicts, fix the UI, and rerun until it works.
SentinelAI is an open-source, local-first CLI that learns your repo, keeps memory in SQLite, and runs 8 agents to detect risks, enforce rules, and suggest fixes using IBM watsonx/Bob without sending raw code.
Code Janitor is an AI-powered code review and refactoring platform that detects bugs, suggests optimizations, visualizes codebases, and provides live previews, built with assistance from IBM BOB, IBM’s AI-powered development assistant.
An Agentic Runtime Firewall that monitors staging environments for crashes. Using IBM Bob's full repository context, it instantly injects memory hot-patches to unblock QA and automatically opens a Pull Request with the permanent fix
A comprehensive QA automation platform for teams to record, manage, and execute automated tests with security vulnerability detection, integrable into CI/CD pipelines via webhooks.
RepoGuardian AI is an AI-powered repository intelligence system that analyzes codebase changes, detects downstream impact, predicts risks, and generates self-healing fixes using graph-based dependency analysis and LLM-powered reasoning.
Stop dreading unfamiliar codebases. Gorango turns any public GitHub repo URL into a plain-English intelligence report with an app summary, tech debt map, and dead code scan in seconds.
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.
Simplify data engineering workflows with an all-in-one VS Code extension for managing ETL tasks.
OptiCode QA is an automated testing tool that bridges local hardware metrics with IBM watsonx.ai to validate if an algorithm is truly stable and scalable before cloud deployment
Cascade analyzes GitHub PRs and unified diffs with IBM Bob Shell—streaming live reasoning and returning a validated blast-radius report (risks, files, tests) before merge.
This solution demonstrates how IBM Bob orchestrates complex data engineering workflows (5-stage medallion architecture with validation) while seamlessly integrating AI predictions via Watsonx.ai.
Sira is an open-source AI-friendly scaffolding CLI that generates production-ready projects with preconfigured AI context files, smart stack recommendations via watsonx.ai, and instant setup for tools like Claude, Cursor, and IBM Bob.
AI-powered tool to analyze GitHub repositories and generate architectural documentation
MissionForge is a CLI-first harness and Bob Skill that turns refactors into scoped, measurable missions. Bob handles code reasoning, while MissionForge tracks scope, baselines, validation gates, reports, and reviewable evidence.
Stop vibe coding. StackForge lets developers snap together architectural blocks (Front-end, Auth, DB) into a visual blueprint. IBM Bob Shell reads this graph to instantly generate repo-ready code that respects your strict constraints.
A command-line tool that integrates IBM Bob into any developer workflow. Explain codebases, scaffold features, generate tests, update docs, and review code - all with simple commands, on any existing project.
BCBob is an AI-powered security fixer built on IBM Bob that automatically scans, audits, and remediates vulnerabilities in AI-generated apps. It provides system-wide patching and sandbox verification to secure rapid "vibe-coded" projects at scale.
NeYO is a enterprise solution AI that will help you build full stack app. Coffee shop or anything else your business idea will be built by give a short or long context to the NeYO chat. In This CLI you can manage ERP and CRM for your business
BobBridge transforms natural language prompts into live mock API endpoints and framework-specific code scaffolds using IBM watsonx.ai. Designed for rapid prototyping, it generates contracts and provides a seamless handoff to IBM Bob for implementation.
Generate production-ready infrastructure code from plain English descriptions using Anthropic Claude
A persistent memory layer for IBM Bob that learns from every correction your team makes — so Bob never repeats the same mistake twice.
Rosetta connects to any SQL Server or SQLite database, inspects its schema, and uses Llama 3.1 AI to instantly generate interactive onboarding documentation — so new developers understand an unfamiliar database in under an hour instead of a week.
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.
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.
A custom IBM Bob mode that transforms Bob into a research code onboarding specialist. Drop the config into any Python research codebase and Bob produces architecture maps, setup guides, and stub detection in minutes, not weeks.
AI Repo Interpreter is an IBM-Bob-powered onboarding tool that helps developers quickly understand unfamiliar codebases through repository analysis, generated insights, and AI-powered Q&A.
NullRift is an intelligent engine for front-end developers that instantly transforms text prompts into ready-to-use React/TypeScript interfaces. The platform shortens the path from idea to production code, completely bypassing the Figma stage.
AI coding agents forget everything between sessions. AstroBob fixes that — an open MCP memory layer on AstraDB that gives any agent persistent, self-teaching memory. Agents remember decisions, recall patterns, and write their own skills over time.
An AI orchestrator turning meetings into production. With directory access, it codes features, drafts emails, and creates docs in real-time. Using zero-latency RAG, it executes tasks so that when the call ends, the work is already complete.
NATS: AI engine translating meeting notes into structured, context-aware tasks for IBM Bob autonomous code changes using Fireworks AI, Watsonx, & GitHub.
BobArchitecLegacyLens transforms legacy code into clean architecture in seconds using IBM watsonx.ai. Upload Java, PHP, Python or COBOL to get ER diagrams, SQL schemas, modern TypeScript, and exportable scaffoldin
AI-powered modernization tool that analyzes legacy codebases and transforms them into clean, modern code using IBM Bob and watsonx.ai. Upload any repo via GitHub URL, ZIP, or local path and get a refactored version with full documentation in minutes.
BobCI deploys 7 specialized AI agents powered by IBM Bob and watsonx.ai to autonomously review pull requests — detecting security vulnerabilities, predicting failures, generating tests, and mentoring junior developers in under 6 seconds.
RepoMind AI uses IBM Bob to understand, document, test, and improve a real-time financial backend built with Kafka, CQRS, and Drools, reducing onboarding effort and accelerating development in complex distributed systems.
Loopr is a recursive AI agent that generates tests, runs them, fixes failures, and learns from every execution. Built end-to-end with IBM watsonx.ai Granite and IBM Bob — it demonstrates its own premise.
AI agents write diffs that pass tests but hide dead code, hallucinated APIs, and vacuous assertions. Verdict catches them 7 static + dynamic checks, one PASS/SUSPICIOUS/LIED scorecard. Ships as CLI, MCP server, Bob Verifier mode, VS Code tab, and CI gate.
An autonomous CLI agent powered by Gemma 4 that turns any source; web, API, PDF, into a typed Parquet dataset with codebook in minutes.
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.
An AI-powered documentation lifecycle engine built for the IBM Bob Hackathon. Automatically parses Python repositories and compiles ready-to-read markdown assets via a clean Streamlit interface.
IBM Bob reads your robot's mission data, finds the bug, fixes it, and tells you if it's safe to deploy — all in under 60 seconds. Built for ROS2. Works on any robot. Drop in one folder and Bob becomes your AI engineer.
odebase Time Machine turns any Git repository into a queryable knowledge base. Ask why code exists, scrub through file history, auto-generate ADRs, and chat with AI-synthesized profiles of past contributors, all powered by IBM Bob.
CodeAtlas is a developer tool that instantly maps GitHub repositories and runs parallel static analysis to uncover dead code, missing tests, and doc gaps. Critical vulnerabilities are enriched with high-speed AI insights which is fixed and reviewed.
BobGoblin automatically analyzes code changes, generates AI powered regression tests using IBM Bob, executes them with Playwright, and predicts release risk before deployment.
Bob Skills Registry turns repeat IBM Bob workflows into reusable, installable skills. It validates skill quality and guides developers through multi-step tasks like API test generation and database migrations with consistent, context-aware execution.
TestForge Pro scans GitHub repositories, generates Jest tests with live AI, and safely opens PRs using a Bob-assisted workflow to convert untested code into reviewable pull requests.
An AI‑powered SaaS platform that automatically analyses legacy codebases, generates architecture maps, technical‑debt dashboards, AI‑driven documentation, and guided onboarding roadmaps.
DevFlow AI is an AI-powered developer productivity platform that helps developers generate SQL, debug Python errors, analyze repositories, and visualize analytics through intelligent AI workflows.
SmartShift uses AI to solve warehouse overload problems. Managers describe issues in plain English, and our CrewAI agents analyze workers using semantic search, delivering optimal recommendations in seconds. Built with IBM Bob as AI partner.
A GitHub-native AI developer workflow assistant powered by IBM Bob that automates repo summarization, documentation generation, unit test scaffolding, and pull request reviews.
BugFinderFixer is an AI-powered web app that scans code in many programming languages, detects bugs and security issues, explains errors in simple terms, and generates corrected code for students, developers, educators, and reviewers.
Bob 360 is an AI guardian watching your full software lifecycle. It detects cascade failures before they happen, cleans dead code safely, translates technical PRs for executives, and traces 3AM server crashes back to the exact commit in seconds.
Paste a GitHub PR URL. BlastRadius traces every downstream call chain across your repository, finds uncovered critical paths, generates missing test stubs, and issues a BLOCK or PROCEED verdict in under 30 seconds.
CognitiveLoop — An AI-powered adaptive learning platform that personalizes education through cognitive profiling, behavioral analytics, and real-time engagement tracking.
QA-AutoSuite is an AI-powered QA automation agent that generates deep, polyglot test suites inside VS Code, integrates into CI/CD pipelines, and deploys as an autonomous AI agent via IBM watsonx Orchestrate.
Context-Aware AI Code Generation Agent that keeps interdependency context, enforces code reuse, prevents AI-induced technical debt, and reduces context bloating & token consumption in enterprise codebases.
Elith gives any AI model — Claude, Gemini, local LLMs — the same repo-aware intelligence that enterprise tools have natively, through a lightweight skill layer and smart context engine that loads only the files that matter.
Bobcat is an interactive architecture canvas for backend codebases. Hover any function to see why Bob flagged it as risky, ask Bob to refactor with a diff preview, or simulate the blast radius of a change. Bob is woven into four UI touchpoints.
AI-powered security IDE that detects code vulnerabilities in real time, explains them 3 ways (Analogy, Technical, Meme), and auto-patches with one click — with HIPAA, GDPR & SOC2 compliance built in.
A practical demo of AI-driven Chaos Engineering. Using PAYO’s offline-to-blockchain setup (SQLite, Holepunch, TronWeb) as a case study, we use IBM Bob to simulate critical network failures, identify race conditions, and automate security refactoring.
Query any dataset in plain English — no SQL required
Audit-grade AI agent that migrates, refactors, and secures production codebases — every patch cryptographically signed, every change traceable, queryable from IBM Bob via MCP
AsyncPair brings pair programming to teams across time zones. When you log off, it captures a structured handoff from your git commits; when your teammate is offline, an AI stand-in answers their questions, grounded in your work and coding history.
CodeHeal is an AI-powered code analysis and auto-fix tool integrated with IBM Bob that detects bugs, performance issues, and code quality problems in Python code instantly.
The first app fully architected & coded by IBM Bob. RepoSense analyzes any GitHub repo in ~9s using all 4 Bob SDK modes — delivering onboarding reports, contextual Q&A, and AI-written code diffs. Zero setup for judges.
An AI-powered extension for IBM Bob that solves two critical developer problems: outdated AI-generated SDK code through live documentation intelligence (DocSync MCP), and automatic research paper generation directly from codebases (Code2Paper).
Compass AI accelerates developer onboarding by using WatsonX to analyze complex codebases. It transforms raw repositories into interactive, step-by-step learning roadmaps and visual dependency constellation graphs.
AIRA autonomously triages, diagnoses, and fixes software incidents using Groq's Llama 3.3 70B and LangGraph. It analyzes errors, generates patches with confidence scoring, and auto-creates PRs or requests human approval—resolving incidents in <30 seconds.
SYNKRO is an AI-powered code security scanner and auto-fixer designed to help developers "Ship Secure Code, Automatically".
AI-powered TODO/FIXME scanner built entirely on Android. IBM Bob analyzes code, generates reports, and exports session logs. Zero hardware cost.
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.
AI-powered desktop app that scans codebases, maps architecture, generates documentation, and produces review findings plus improvement suggestions using static analysis and optional IBM watsonx.ai enhancements.
MeetFlow transforms meeting transcripts into code-aware Jira tickets automatically. It indexes your codebase,identifies action items, and generates implementation-ready tickets with exact files and steps — then Bob IDE with MCP implements them end-to-end.
An AI-powered project that helps developers improve existing code by analyzing the repository to see its content, suggesting potential improvements, automatically generating documentation and tests, and more.
Bob By Your Side, your AI teammate who never clocks out. 5 specialized modes cover your full dev lifecycle. Never lose a requirement. Never forget a decision.
Meet BobOps — an AI-powered self-healing DevOps platform that monitors production systems, analyzes failures, generates fixes, validates them, and ships production-ready GitHub PRs autonomously.
A compliance copilot for AWS Terraform that runs inside IBM Bob. Cites ASEAN financial regulators from a deterministic corpus. Ships a regulator-grade evidence pack in twelve seconds.
An AI-powered e-commerce analytics platform that safely transforms natural language business questions into lightning-fast, secure PostgreSQL queries through an optimized data pipeline and robust backend bastionining.
AI agent orchestration runtime built around Chimera Pilot — a resource-control layer that compiles natural-language objectives into a task
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.
Your entire Vultr network, on a single rotating globe. Atlas is a real-time 3D operations cockpit for Vultr. See every active region, every server, every load balancer, every database, every maintenance event.
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.
The World's First Embedded System and Circuit Simulator, for secondary school to degree students and hobbyist wanting to learn hardware
Autonomous multi-agent research system that continuously improves enterprise RAG pipelines
An AI-powered debugging assistant that detects, explains, and automatically fixes coding errors while optimizing performance and improving code quality for developers.
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.
Complete ROCm harness featuring the ROCm compiler, profiler, specialized skills, and intelligent agents. Converts CUDA code to HIP and optimizes it for performance on MI-300x platforms.
Shared context compiler for multi-agent LLM systems. Cuts token usage 79%, VRAM 68%, TTFT 7.8x. Implements TokenDance, JCR Safety Gate & KVCOMM on AMD MI300X. 310 tests passing, 15/15 benchmarks.
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.
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.
Wave Engine is an agentic app builder that generates, repairs, validates, and packages full web projects using a MAS-first autonomous repair loop, with LLM calls only when static agents cannot fix issues.
DREAMWEAVE is a cognitive memory framework a layered retrieval middleware that sits between raw data and any large language model, transforming how AI systems store, organize, retrieve, and reason over knowledge.
Two LLMs audit a small MoE model's reasoning, identify failure-correlated layers via statistical attribution, and train LoRA-DPO targeting only those layers. Validated end-to-end on DeepSeek-V2-Lite; held-out eval pending controls.
RTL Repair is a fine-tuned Verilog/SystemVerilog bug repair assistant that takes design intent and buggy RTL, then returns fixed RTL, a bug explanation, and a verification suggestion.
Faultline is a multi-agentic platform to simulate how real users fail, abandon, misunderstand, and exploit software before release.
Forma is a Chrome extension that catches vague UI vocabulary in vibe coders' prompts on v0, Cursor, Lovable, and Bolt — rewriting them with canonical component terms. 7 agents on AMD MI300X: Llama 3.1 8B for real-time scoring, 70B AWQ for Memory Engine.
SKT-OM is a powerful 13B LLM integrated with SKT RAG and LangGraph on AMD ROCm. It delivers intelligent, multi-step reasoning RAG system with agentic workflows, tool calling, stateful memory and high-accuracy responses.
ProfiloAI turns AMD GPU profiler output into a plain-English diagnosis, root cause, code fix, and expected speedup for ROCm developers.
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.
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.
AI agent orchestrator (Auditor and Builder) and fine-tuned Qwen2.5-14B models for automated code vulnerability detection & secure patch generation, optimized for AMD ROCm 7.0 + MI300X.
TITAN-ROCm is an AI-powered GPU optimization system that analyzes PyTorch CUDA code, generates optimized variants using an LLM, benchmarks performance in real time, and selects the best implementation through autonomous optimization and profiling.
Multi-agent system using AMD MI300X + Qwen2.5-Coder with planning, coding, review, and execution
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.
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.
Ghost-Coder is an autonomous AI agent powered by Qwen2.5-Coder-32B and AMD MI300X that dynamically translates, verifies, and self-heals CUDA kernels into AMD ROCm/HIP code, accelerating cross-platform GPU migration.
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.
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.
ROCmPort AI is a 5-agent pipeline that migrates CUDA kernels to AMD ROCm/HIP. It detects hardware-specific bugs hipify misses, compiles with hipcc, profiles with rocprof on real MI300X hardware, and iterates until the output is correct and optimized.
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.
Repo-Insight replaces vector RAG with Graph-RAG — ingesting the repo into a structural graph that grounds the agent and prevents hallucination on long coding sessions.
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.
PatchPilot AI is a generic agentic code review copilot for C++, Java, JavaScript, Python, and C#. It analyzes simple and complex code, detects bugs, security issues, and performance bottlenecks, then generates fixes and test plans.
A fine-tuned Mistral 7B language model with Chain-of-Thought reasoning for understanding codebases, generating code, and answering developer questions. Built with AMD ROCm support for accessible AI development.
Al Agent Orchestrator for Real-Time Engineering Simulation. Powering the next generation of CAD/CAE workflows on AMD ROCm™ hardware.
A fine-tuned 7B LLM that converts PyTorch, CUDA, and Triton code into hand-tuned HIP kernels optimized for AMD MI300X — with wavefront-64, MFMA intrinsics, and gfx942-specific optimizations the base model never produces.
Multi-agent AI copilot that diagnoses bugs, reviews diffs, and gates deployments , grounded in your actual codebase via Graph-RAG. Deterministic security pre-scan catches backdoors before the LLM even runs.
AI system that transforms doctor–patient conversations into structured medical intelligence: SOAP notes, ICD-10 codes, drug safety checks, and clinical risk scoring — in real time using a multi-agent reasoning pipeline.
ROCmPilot is a multi-agent AI system that scans CUDA-first GitHub repos and generates ROCm migration findings, patch previews, validation plans, and reports.
ROCmForge is a multi-agent migration lab that converts CUDA projects to run on AMD hardware. It scans repositories to detect NVIDIA dependencies, generates optimized ROCm patches, tests execution in a secure sandbox, and produces benchmark reports.
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.
CodePause is a reproducible LoRA/QLoRA prototype that fine-tunes a code model to insert removable Think-Anywhere reasoning blocks during code generation, then strips them and evaluates executable Python with tests.
Simulates zero-trust agents exchanging data, where a Researcher pays USDC nanopayments to unlock premium insights from a Provider.
We are a team from Nepal building BrandAgent ARC — an AI system that helps brands grow smarter through automation and real-time decisions.
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.
Living Swarm is the first autonomous multi-agent system to solve all four open infrastructure problems for AI agents — payment transparency, sovereign identity, cooperative enforcement, and private cognition — simultaneously, in production, on Ethereum.
Launchium transforms any startup idea into a launch-ready package in hours — validated business concept, MVP code, security audit, and marketing kit — all powered by 8 specialized AI agents working in parallel. Ship faster. Build smarter.
Pleiadesian — a constellation of 7 autonomous AI agents that build, research, communicate, protect, analyze, create, and coordinate together. Multi-agent orchestration in action.
SkillForge is an AI-powered skill generator for OpenClaw. Describe what you want your agent to do, and get a working, security-scanned SKILL.md in seconds -- with streaming generation, format validation, and risk scoring.
HALE (Heuristic Autonomous Logical Evaluation) Oracle is the first autonomous forensic auditor built to bridge the "Trust Gap" in the machine economy. It enables AI agents to transact capital securely by using Google Gemini to audit digital deliverables .
Sentinel is an autonomous QA system powered by AI agents (LangGraph + GPT-4o + Claude Code) that runs Playwright tests, auto-fixes failing CI code, and creates Pull Requests with human approval via Slack.
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.
AI security platform where three agents work together: WAF that classifies threats, Pentester that finds vulnerabilities, and Red Team that attacks the WAF whose bypasses automatically strengthen the WAF's detection, creating a self-improving defense loop
Multi-layered AI firewall that detects and blocks prompt injection attacks in real-time. Features 5 defence layers, adaptive learning, zero-day detection, and explainable AI with <500ms latency and <2% false positives.
GenAI Giants empowers developers with AI-driven tools for learning, productivity, and innovation. Built for inclusivity, it supports multiple Indian languages, cloud-native workflows, and scalable solutions to bridge knowledge and technology for all
AI gateway that routes requests to the best API, pays providers with our credits, and charges users per-use in USDC with transparent pricing.
Kynet is a "Capability Network" that makes AI agents anti-fragile. Built on Arc & USDC, it lets agents escalate from buying code tools (Streams) to generating them via Gemini (Genesis), or hiring humans for edge cases (Relay) to ensure task completion.
Goodbye to permanent API keys. AgentPaywalls replaces static .env credentials—prone to abuse and rate-limit issues—with short-lived, payment-verified tokens. AI agents pay per request using USDC on Arc for secure, usage-based access.
A decentralized chat session and memory layer with Circle, Pinata and ARC network based system V1.
The first AI dual-mode agent for Qubic. Instantly generates secure C++ smart contracts from natural language and scans existing code for vulnerabilities. Features gas optimization and instant audit reporting in 54+ languages
VisionFlow uses IBM watsonx Orchestrate to orchestrate 5 specialized AI agents for supply chain quality control using Vision (box quality) and OCR (label extraction) to automate the tedious manual error prone , human verification with 96% success
LegacyLift is an AI-powered enterprise modernization platform that automatically converts legacy COBOL code into production-ready Python using IBM WatsonX Orchestrate and Granite models, while generating clear documentation and explanations.
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.
CodeSync creates specialized AI agents trained on the latest official documentation from any framework or library. Stop getting outdated code from generic AI—get accurate, up-to-date answers powered by RAG, Qdrant, and Gemini AI.
Nrityapath converts natural-language movement or story descriptions into structured Bharatanatyam choreography using NNF—an AI-enforced JSON schema—powered by a full Opus workflow and displayed through a visual step-by-step prototype.
SmartRefactor is an AI-powered coding assistant that simplifies code refactoring, making it faster, cleaner, and more efficient. With intelligent analysis, multi-language support, and real-time optimization,—like Grammarly, but for code.
The AI Dev Squad is a revolutionary multi-agent AI system. It features specialized AI agents that collaborate through the Coral Protocol to provide intelligent software development assistance.
Turn your ideas into ready-to-install WordPress plugins in minutes. Chat with our consultant agent, then let our developer agent generate and package your plugin for instant download—no coding required.
GreenSage is a VS Code extension that analyzes your code and suggests energy-efficient improvements based on Green Software Foundation guidelines, helping developers reduce energy use, optimize performance, and write sustainable code.
DevFlow AI: a Next.js-specific, AI-powered no-code/low-code platform that transforms plain ideas into fully functional applications.
An interactive Streamlit app that acts as an AI coding mentor. It adapts to user skill level, analyzes questions, streams step-by-step explanations with examples, auto-continues long answers. Powered by the GPT-5 model through the AIML API.
Legacy Linter Ultimate is AI-powered development partner that uses GPT-5 to not just refactor legacy code, but to automatically document, audit, test, and visualize it, turning technical debt into a documented and reliable asset.
A modern AI Developer Dashboard built with Next.js, Tailwind CSS, and TypeScript—featuring real-time code assistance, code review, rapid prototyping, and automation tools to boost developer productivity in one intuitive interface.
Multi-Agent AI VS Code Extension — A powerful AI coding assistant featuring real-time code completion, security analysis, and intelligent documentation, driven by specialized agents in a unified VS Code interface.
ServeTheVibe is an AI-powered music co-creation tool that transforms your humming and text prompts into playable music and live Strudel code, enabling instant idea capture, fast demos, and creative coding for musicians and enthusiasts.
An AI-powered developer tool that instantly generates a complete, production-ready Hono.js backend, including a full project structure and boilerplate, directly from an OpenAPI specification.
A modern solution built with React and TypeScript, featuring dark/light theme, local storage persistence, search functionality, and tag-based organisation. Perfect for developers to store, search, and manage frequently used code snippets efficiently.
Convert any wireframe into a fully functional app in seconds!
A custom MCP server that powers AI agents inside the Trae IDE. It enables automated system flow mapping, allowing developers to visualize and interact with control/data flows across large codebases in real-time.
Auto-generate professional README.md files from Python projects using an agent-based AI system
A generative AI-powered application that transforms written text into natural, human-like speech using cutting-edge language models and advanced TTS techniques. The system features an intuitive interface built with tool like Gradio for easy use.
AGO is an AutoGuided Onboarding chat flow that centralizes CFO reduction project’s communication. It automates scheduling, sends reminders, answers project queries, and gathers feedback to boost efficiency and streamline collaboration.
Modernize obsolete code effortlessly: import your project, generate use case and class diagrams with summaries, and convert legacy code to a modern language of your choice.
CodeNova is an AI-powered coding assistant for code generation, debugging, refactoring, and documentation. It's unique features, like text & voice explanations and an AI Coding Partner, enhances efficiency and collaboration.
Validly combines the creativity of LLMs with formal methods from computer science to safely rewrite code automatically. To start with, we’re tackling legacy code modernization from COBOL to Java.
The "Kaggle Baseline Generator with CamelAI" is a project aimed at automating the creation of baseline models for Kaggle competitions, providing competitors with a starting point for their data science challenges.
PRC aims to democratize access to space data through AI agents. This proposal outlines the development of a foundational model focusing on data retrieval, educational engagement, and citizen science participation.
EduNexus 2.0 is a AI Learning platform for Students ( School ,College , University ) which offer Personalized learning, Real-time support, Smart summaries, coding mentorship, and mental wellness resources.
A VS Code extension to help developers with development using Llama AI, supporting native language prompts.
CursoAIr - is a plugin developed for enhancing the capabilities of Cursor Code Editor by using some more features like Code Generation, Optimization, Debugging and AI for all purposes!
Helping business users plan AI solutions. Bridging the gap between business users and their future AI projects through a series of useful insights. We provide: 1. A project brief 2. Market analysis 3. Competitor analysis 4. Technical components
An AI-driven tool that generates optimized code in various programming languages, allowing users to compare results from multiple models and visualize time and space complexity.
The AI-Powered Quantum Algorithm Designer is an innovative application that harnesses the capabilities of OpenAI’s advanced o1 reasoning models to assist users in designing and visualizing quantum algorithms.
CoLlama will help you learn programming by teaching you 1) how to do assignment questions 2) how to go from where you're currently at to where you want to be.
Meet Dev AI Agent, a cutting-edge coding assistant running on your local machine. Powered by Llama 3.1, it effortlessly handles complex tasks, boosting your productivity by coding from 0 to 1 and transforming your ideas into a functional application.
Quanta is an advanced AI agent that analyzes GitHub repositories to identify security vulnerabilities, performance bottlenecks, and potential bugs. Using open-source models, it provides comprehensive code analysis without compromising data privacy.
Generating synthetic datasets using Llama-3.1 for function calling to enhance small language models for text-to-action capabilities.
Revolutionizing Code Transformation, Explanation, Error Detection, and Test Case Generation with CodeAI
Too tired of reading long API documentation and making errors here and there? There are too many things going on in API interfacing. Let the AI work its magic so you can sit back, relax, and be worry-free about complicated API integration.
RefactorGenie, your code refactor genie. Making code smart and efficient for everyone.
Code Assist+ boosts dev speed with AI & NLP. Review, debug, document, convert code effortlessly. Powered by Codestral.
Welcome to CodeSage 💻🧙♂️ The ultimate interactive debugging tool.
King Coder is a web application that is powered by Codestral from MistralAI. It is a one-stop solution to all the problems faced by coders, be it anyone (professionals, learners or market leaders). Helps to write code, practice DSA, translate code etc.
Our project automates the conversion of wireframes into Python code using advanced language models like LLaMA3 and Codestral, along with the Django framework. This integration streamlines software development, enhances accuracy, and boosts productivity.
Zax Code Assistant is a chatbot designed to generate code snippets and assist with coding tasks. It uses Mistral’s AI API, Flask, Langchain, python on the backend, and HTML,CSS and Javascript.
CodeBaseBuddy with Codestral is a privacy-preserving tool for semantic code search and accelerated onboarding. Leveraging Ollama’s locally deployed Codestral, it guides users through tasks in new codebases, enhancing onboarding time and learning
This project involves developing an AI-powered coding assistant using Langflow, Llama 3, and Streamlit. The project is divided into six phases, each focusing on a crucial aspect of the development process.
QuantumAI is addressing the challenge of navigating multi-dimensional space. In this hackathon, we demonstrate the operational infinite 2D Canvas by creating two helper applications: a Custom Abjad GPT prompt creator and a large number tokenizer.
Viable Trends* per day on day occurrence across a few sectors.
The Text-to-Image Generation project utilizing Hugging Face showcases the fusion of advanced natural language processing and computer vision technologies.
Your ultimate bug-fixing buddy! AI-powered deep-level debugging saves time, boosts productivity, and ensures on-time delivery of high-quality software.
Meww is an innovative chat application that integrates coding capabilities. It provides a unique platform for users to communicate and collaborate on coding projects
Introducing an AI-Driven Dev Tool leveraging Phi-2 for real-time code analysis, predictive project insights, and AI chat guidance, boosting developer productivity and project efficiency.
Polisplexity merges AI, VR/AR, and mathematical modeling for urban planning. Its new feature transforms city photos into animated videos, enhancing realism and engagement in city simulations and management.
Polisplexity is an advanced platform for city management, integrating AI, VR/AR, mathematical modeling, and Google Gemini. It supports city creation, administration, evolution, and simulation, fostering innovative, efficient, and inclusive city.
Data Tonic is the first multi-nested agent-builder-of-agents! A Data-Capable AGI-style Agent Builder of Agents , that creates swarms , runs commands and securely processes and creates datasets, databases, visualizations, and analyses.
Applying Bayesian Principles to Everyday Problems | A cognitive aid to break down decisions into a computable bayesian framework
My creation, a Multilingual Speech Recognizer & AI Assistant, embodies innovation at its core, utilizing cutting-edge tools and technologies to redefine the way we communicate and interact with information.
Developed an AI Agent using AutoGen, that profiles, tracks line by line execution and debugs Python code, enhancing efficiency of debugging identifying logical errors in a proof-of-concept program.
Introducing "CodeBase Buddy" - An advanced retrieval augmented generation system powered by GPT that helps newcomers onboard to a GitHub repository by guiding them on which files to modify and how to implement their first task.
GenieFront : Transforming visual web designs into live sites using Azure, Keras-OCR, & GPT-4. Bridging design and development seamlessly.
Polisplexity revolutionizes urban planning with AI-driven simulations. Explore city scenarios, make data-informed decisions, and shape vibrant, sustainable communities
Leverage generative models for LaTeX code autocompletion... because science gotta go brrrr
Leveraging researchers and Software Engineers to get insights of docs and generate code
The Human Emulation System (Coding Edition) is a sophisticated artificial intelligence pipeline developed during the StableCode Hackathon. The project aimed to create multi-perspective code patterns that blend logical precision and creative nuance.
Intelligent chatbot streamlining the process of development with AI and making development process smoother.
The Interactive Coding Tutor is a web app aiding novice programmers in learning coding concepts effectively. It offers instant feedback, suggestions, and explanations during coding exercises, fostering skill improvement.
Polisplexity is your next-gen solution to the global urbanization crisis! Melding open generative AI, code simulations, and VR, we offer an unprecedented toolkit for tackling city complexity. Transform cities and elevate quality of life now!
Our code instruction generator is a tool that can automatically generate step-by-step instructions for completing a coding task from natural language descriptions.
We use StableCode to generate a database interface agent.
The idea was to develop an Autonomous AI Agent for software testing.
CreatiVerse is a cutting-edge AI project technology aimed to provide an innovative solution to empower elementary school teachers in creating captivating poems and stories for their students, along with images and lyrics.
Introducing Voice CLI: Revolutionary terminal powered by ElevenLabs Voice AI. Node.js backend, React.js frontend, and state-of-the-art NLP for seamless voice-based shell commands execution. Explore the limitless possibilities!
AI-Powered Discord Bot that helps you pick the right AI tool as per your need
We have created a prototype in which user who has to create a website regarding his/her business would fill a simple form describing his/her business details. The website would be generated by AI.
Intelligent static code analysis, right in your IDE
SQLGenius is a smart tool that assists C-Suite executives in querying databases in the plain English language and returns retrieved results with an option to download the data in CSV format and visualization if needed.
An AI coding plugin for the Jetbrains suite of IDE's
An Al-powered, Visual Studio integrated tool to revolutionize code review practices, boosting code quality, efficiency, and collaboration.
Powered by the Claude AI assistant, C3 can help you do anything in the terminal with natural language prompts.
ClaudeCode uses Claude API to automatically do data analysis for you.
An AI Powered Website Generator that converts a resume into website in seconds
Revolutionize your coding experience with our optimization tool. Supports 160+ languages. Clear explanations and powerful optimization features. Perfect for developers, programmers, and coders of all levels. Get started today.
Our application encrypts speech input messages using OpenAI Whisper and multi-layer encryption codes generated by GPT3. Customizable encryption algorithms and keys, user-friendly interface, and easy code retrieval make it ideal for secure messaging.
EasyQuery is a platform that unleashes the intuitive power of Web3 data query with LLM. With its ability to transfer human language into SQL queries and to extract data insights, it is the ultimate tool for unlocking the full potential of Web3 data.
Our app provides a fully digitalized package for our clients. We offer a range of services, including the creation of a logo, ads that can be used on social media platforms such as Facebook and Instagram, a website, and marketing videos
Magilink's tool converts natural language to website components, accelerating website development. Streamlining the process, it saves time and resources for designers, developers, and creators.
ScheduleGenius is a revolutionary project aimed to making it easier for people to manage scheduled tasks by parsing and generating CRON syntax from plain text.
Revolutionize your coding experience with our optimization tool. Supports 160+ languages. Clear explanations and powerful optimization features. Perfect for developers, programmers, and coders of all levels.
All apps loaded