OpenAutoCoder/live-swe-agent

Live-SWE-agent: live, runtime self-evolving software engineering agent

50
/ 100
Established

This project offers a self-improving AI agent designed to tackle software engineering problems. It takes a real-world software issue as input and autonomously evolves its capabilities to produce a working solution or fix. This tool is for AI researchers and developers who are building or evaluating large language model (LLM) based software agents.

310 stars.

Use this if you are developing or benchmarking AI agents for software engineering tasks and need a robust, self-evolving framework to evaluate their performance.

Not ideal if you are an end-user developer looking for an AI assistant to write code directly for your application, as this is a research and benchmarking tool.

AI agent development LLM evaluation software engineering AI AI research model benchmarking
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 13 / 25
Community 17 / 25

How are scores calculated?

Stars

310

Forks

36

Language

License

MIT

Last pushed

Jan 19, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/OpenAutoCoder/live-swe-agent"

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