MLSysOps/MLE-agent

🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Anthropic, Gemini, Ollama, etc supported. :fireworks: Code RAG

58
/ 100
Established

Implements a multi-agent system with autonomous code execution, debugging loops, and built-in defect detection through debugger-coder interactions. Provides local RAG capabilities for project-specific context, file system introspection, and integrated access to research repositories (arXiv, Papers with Code) for SOTA method discovery. Supports autonomous task completion in end-to-end ML workflows including Kaggle competitions, with CLI, web UI, and Discord interfaces alongside core LLM flexibility.

1,524 stars and 61 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 14 / 25
Maturity 25 / 25
Community 17 / 25

How are scores calculated?

Stars

1,524

Forks

103

Language

Python

License

MIT

Last pushed

Jul 27, 2025

Monthly downloads

61

Commits (30d)

0

Dependencies

22

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/MLSysOps/MLE-agent"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.