.png&w=256&q=75)
🤝 Top Collaborators
.png&w=640&q=75)
.png&w=640&q=75)
🤓 Latest Submissions
GemmaRoute The Financial Firewall for EnterpriseAI
GemmaRoute is the financial firewall for enterprise AI infrastructure. The core problem: enterprises today route every customer support query, including trivial ones like "What are your business hours?" to expensive frontier cloud models, burning margins and wasting compute. GemmaRoute solves this with a 4-layer hybrid routing pipeline powered by Gemma 2 running on AMD ROCm hardware. Layer 0 is an instant pre-classifier that detects high-signal vocabulary (legal, SLA, fraud, contract) in zero milliseconds and bypasses the AI classifier entirely for unambiguous queries. Layer 1 runs a local Gemma 2B semantic classifier on AMD hardware, assigning every query a complexity tier. A confidence gate ensures low-confidence results are automatically bumped to a stronger tier. Layer 2 routes to the cheapest capable model: local Gemma 2B for simple queries at zero cost, and cloud models via Fireworks AI for medium and complex queries only when necessary. Layer 3 runs a local Gemma 2B quality judge that scores every response from 0.0 to 1.0 against a 4-criterion rubric. Any response scoring below 0.75 triggers automatic escalation to the next tier, with a hard cap of 2 escalations to prevent runaway costs. The system includes a production-grade circuit breaker that trips after 3 consecutive cloud failures and instantly reroutes all traffic to local AMD hardware for 60 seconds. Exponential backoff retries transient errors at 1s, 2s, and 4s intervals. A hop budget prevents infinite escalation loops. Gemma 2 powers all three intelligence layers: the routing brain, the local executor, and the quality judge, making GemmaRoute the only submission using Gemma in three distinct roles simultaneously. Built with FastAPI, LangGraph StateGraph, SQLAlchemy async, and a Next.js 16 frontend deployed on Vercel. 52 automated tests, all passing. Live demo at gemmaroute.vercel.app.
13 Jul 2026
AuraGrid — AI-Powered DePIN Migration Network
AuraGrid is a decentralized physical infrastructure network (DePIN) that uses AI agents to keep computing workloads alive during power outages. When a node loses power, AuraGrid automatically detects the crisis, selects the best available node using a LangGraph AI state machine, migrates the task with zero data loss, and narrates every decision through a Band AI agent powered by Phi3 running locally via Ollama. Built for regions with unstable power grids — starting with 13 nodes across 10 African countries — AuraGrid ensures that solar-powered edge nodes collaborate intelligently to maintain uptime. How it works: 1. Edge nodes stream live telemetry (battery, CPU, RAM, power source) to the coordinator 2. LangGraph brain (4 states: MONITORING → CRISIS_DETECTED → MIGRATING → RESTORED) decides where to move the workload 3. Migration engine selects the highest trust score node as target 4. Band AI Agent narrates the decision live using Phi3 AI 5. Dashboard updates in real time showing all nodes across Africa Tech Stack: Node.js, Express, Socket.IO, PostgreSQL, Prisma, LangGraph, Phi3, Ollama, Band AI SDK, Next.js, Vercel, Render
19 Jun 2026
