tang-vu/ContribAI
Autonomous AI agent that contributes to open source — discovers repos, analyzes code, generates fixes, and submits PRs
Built on a modular pipeline with 20+ specialized analyzers (security, performance, refactoring) that route tasks across multiple LLM providers (Gemini, OpenAI, Anthropic, Ollama) based on complexity. Features a multi-round "hunt mode" for autonomous repository discovery, a "patrol" system that monitors submitted PRs for review feedback and auto-fixes code, and integrates as an MCP server for Claude Desktop—all backed by SQLite in-memory state management and Docker-based code validation. Includes safety gates (quality scoring, duplicate detection, CLA compliance, AI policy respect) and extensible plugin architecture for custom analyzers.
182 stars.
Stars
182
Forks
74
Language
Python
License
—
Category
Last pushed
Mar 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/tang-vu/ContribAI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
judge0/judge0
Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.
kodustech/kodus-ai
AI Code Review with Full Control Over Model Choice and Costs.
web3infra-foundation/mega
Mega is an open-source implementation of Google Piper — a Git-compatible monorepo engine built...
redwoodjs/agent-ci
Agent-CI is local GitHub Actions for your agents.
probelabs/visor
Visor — AI workflow engine for code review, assistants, and automation. Orchestrates checks, MCP...