Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
Every interaction makes your AI team smarter. Agents Terminal V3 is a self-improving orchestration platform. WhatsApp messages flow through a 7-intent classifier, get captured and automatically upgraded every Saturday — smarter week after week.
TipFork is an AI menu agent: snap a restaurant menu and it extracts every dish and price, translates dish names, generates AI visuals of each dish, and estimates tax and tip with a fair per-person split, reconciled against the real receipt.
Clark is a general-purpose autonomous web agent. Give it a goal in plain language and it opens a real browser, reasons through the task step-by-step, and executes actions.
CashFlow AI is an agentic AI platform that automates debt collection for businesses through intelligent reminders, payment tracking, accounting integrations, and human-in-the-loop workflows to maximize recoveries and reduce manual effort.
The AI-Driven Onboarding and Customer Success Workspace is a dual-purpose platform that accelerates user ramp-up through interactive, scenario-based evaluations.
Zero-cost, WhatsApp-native AI employee for SMBs that negotiates bulk orders and auto-generates invoices in code-switched Hinglish/Taglish, routed through a compute-saving cascade router built on Gemma-class architecture.
Kernel Olympics is a multi-agent AI pipeline that automatically ports NVIDIA CUDA kernels to AMD ROCm/HIP — transforming weeks of manual engineering into ~2 minutes per kernel with 3-stage validation gates and real GPU verification.
YOUSUN Axion turns messy AI workloads into AMD-ready deployments by scanning code, detecting CUDA/ROCm issues, suggesting fixes, benchmarking improvements, and creating a professional readiness report.
An AI-powered healthcare data analysis platform that visualizes patient datasets, performs interactive analytics, and generates intelligent healthcare reports using Llama 3.2 via Ollama to support faster data-driven clinical decision making.
An AI document-compliance agent that turns raw English drafts into fully formatted UN Secretariat reports enforcing real DGACM/UN Editorial Manual rules using MiniMax M3 on AMD Instinct (via Fireworks AI) for fixes that need editorial judgement compliance
GemmaRoute is a 4-layer hybrid AI router that cuts LLM API costs by 80%. Local Gemma 2B on AMD ROCm handles trivial and simple queries for free. A Gemma quality judge auto-escalates to cloud only when response quality demands it.
A secure edge-to-cloud AI agent for finance. VaultEdge intercepts enterprise data, scrubs PII locally on AMD hardware, and routes anonymized tasks to the Fireworks API. It guarantees privacy while slashing cloud API costs.
AgeBand — privacy-first passive age assurance for chat. An LLM infers an age band from how you write; a deterministic shell decides band, confidence, and safety posture, so it can't be confidently wrong. On-prem on AMD MI300X/ROCm/vLLM.
Livora AI is an AI health companion that helps users understand, monitor, and improve liver health by combining medical reports, ultrasounds, biomarkers, and lifestyle data into personalized risk scores, progress tracking, and preventive guidance.
AI assistant that reads your support inbox, auto-replies to routine questions, escalates complex issues with reasoning, and shows you why — powered by Gemma 4 on Fireworks, AMD ROCm embeddings, and Convex realtime.
AI-powered meeting preparation assistant that combines real-time web research via Exa neural search, persistent memory via Mem0, and Gemini 2.0 Flash to generate 30-second meeting briefs for sales teams.
BrainOS transforms enterprise documents into executable AI skills — not another document chatbot, but a structured knowledge layer an AI agent can reason over and act on, with full transparency into every step.
An autonomous AI Tier-3 support engineer that automates technical SaaS operations by securely reasoning over codebases, database records, server logs, and recent Git history using a secure SQL Security Guard and AMD-optimized local LLMs.
AgriSense AI turns Sentinel-2 satellite data into simple, actionable crop advisories for Haryana farmers using NDVI/NDWI health indices and an AI reasoning agent for real-time irrigation and crop guidance.
Hunter Foreman uses Fireworks AI to turn scattered customer requests into owned, traceable business work through intelligent classification, live dashboards, task visibility, and connected-app orchestration.
A high-performance solar fleet intelligence and dispatch automation platform that calculates real-time soiling losses and automates technical field routing via WhatsApp, accelerated by an AMD ROCm pipeline and live Firebase architecture.
Anirvium unifies autonomous execution, plan-driven reasoning, policy governance, and trajectory intelligence. Sarvagun resolves customer-support workflows; SuperTuriya traces every decision, learns from outcomes, and improves what happens next.
Agro-Pilot AI is an AI-powered smart farming platform that helps farmers make data-driven decisions using weather, market insights, and crop analytics.
ProofGate coordinates five Band agents through structured `proofgate.band.v1` handoffs to plan, resolve, isolate failures, retry once, and deliver one terminal result.
Incident Room is a Band-powered multi-agent investigation desk that detects when AI support agents claim success but backend tools fail, then turns failed chats and call traces into auditable incident reports.
ClaimGuard: a 4-agent insurance claims pipeline on Band. Assessment and Payout actively query a deterministic Compliance Firewall over Band for data clearance before acting — real governance negotiation, not a static data filter.
DocLine is a platform that triages NHS 111 calls with a team of AI agents through Band, AI/ML API & Featherless. Agents collaborate to run patient intake with shared context & cross-function communication, improving efficiency & reducing manual workload.
A multi-agent cybersecurity operations platform that automates incident response, threat intelligence, MITRE ATT&CK mapping, analyst workflows, and executive reporting through coordinated AI agents.
LaunchGate AI is an AI release gatekeeper that simulates production risk before deployment by running multi-agent “pre-flight checks” across security, QA, compliance, and ops signals.
Loopkeeper uses a band of AI agents to track accountability in B2B workflows - detecting who holds the ball, reading the inbox for escalations, scoring case health, and triggering playbook rules so nothing falls through the cracks