SWE-agent

LM-driven harness built for SWE-bench: edit state, command execution, and issue-focused loop—the reference agent stack next to the benchmark itself.

memoryevalspython
Stars
19.6k
Adoption surface
slightly complex
Autonomy
headless
Recovery
resumable
License
✅ open-source
Category
Coding harness configs and SDKs

Repository ↗ Example: Default agent config ↗

Related in Coding harness configs and SDKs