Local-first autonomous coding agent (Claude Code/OpenDevin-style) on Ollama qwen2.5-coder — agent loop, tool calling, Docker sandbox, FAISS memory, FastAPI + React
-
Updated
Jun 14, 2026 - Python
Local-first autonomous coding agent (Claude Code/OpenDevin-style) on Ollama qwen2.5-coder — agent loop, tool calling, Docker sandbox, FAISS memory, FastAPI + React
A guard-railed, closed-loop workflow for AI coding agents: live state bus + execution-level hard intercepts on Claude Code (GitHub PR / GitLab MR). From step-level to requirement-level — eval-driven, spec-driven, human-in-the-loop.
Autonomous AI-powered cloud agent — generates code fixes, validates in isolated cloud sandboxes (AWS Fargate/Docker), and opens pull requests automatically. Multi-LLM support (Claude, GPT-4, Groq). Built for developers, SREs, and platform engineers.
Autonomous AI Cloud Agent 2026: Auto-Fix Code & PRs with Multi-LLM Sandbox
Add a description, image, and links to the autonomous-coding-agent topic page so that developers can more easily learn about it.
To associate your repository with the autonomous-coding-agent topic, visit your repo's landing page and select "manage topics."