# mini-swe-agent

> Minimal open-source software-engineering agent from the SWE-bench/SWE-agent team: about 100 lines of Python, bash as its only tool, a linear history, any model via LiteLLM.

- id: `mini-swe-agent`
- category: Harnesses (`harnesses`)
- url: https://mini-swe-agent.com/latest/
- repo: https://github.com/SWE-agent/mini-swe-agent
- docs: https://mini-swe-agent.com/latest/
- status: active
- pricing: open-source
- license: MIT
- tags: coding-agent, cli, python, swe-bench, open-source
- related: SWE-bench (https://indexagentica.com/entries/swe-bench/); SWE-smith (https://indexagentica.com/entries/swe-smith/); OpenHands (https://indexagentica.com/entries/openhands/); Aider (https://indexagentica.com/entries/aider/)
- sources: https://github.com/SWE-agent/mini-swe-agent , https://mini-swe-agent.com/latest/ , https://pypi.org/project/mini-swe-agent/
- added: 2026-10-18
- updated: 2026-10-18
- last verified: 2026-10-18
- featured in: Agent benchmarks compared (https://indexagentica.com/compare/agent-benchmarks/)
- maintainer: SWE-agent team (Princeton & Stanford)
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/mini-swe-agent/
- json: https://indexagentica.com/api/entries/mini-swe-agent.json

Each action runs independently with `subprocess.run`, so swapping in `docker exec` or another sandbox is trivial. Runs locally or in Docker/Podman, Singularity/Apptainer, bubblewrap and more. The README reports >74% on SWE-bench Verified, and it is the scaffold behind the SWE-bench (bash only) leaderboard. From the team behind SWE-agent and SWE-bench. Installs from PyPI as `mini-swe-agent`.