Ankan-Das/CodeCourt
CodeCourt is a multi-agent PR review system where AI agents debate your code changes — a Defender argues for the code, a Prosecutor challenges it, and a Judge delivers the final verdict. Includes security scanning (OWASP Top 10), auto-fix patch generation, and support for OpenAI, Anthropic, and local models via Ollama.
Stars
—
Forks
—
Language
Python
License
—
Category
Last pushed
Mar 15, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Ankan-Das/CodeCourt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...