mini-swe-agent
github.com/swe-agent/mini-swe-agent- Category
- AI Agents
- Rank
- No. 793Tools index
- Pricing
- Open Source
- Platform
- cli
- Type
- TOOL
- Builder
- swe-agent
- GitHub
- 6.8k stars
- Latest release
- v2.4.6
- Date
About
A minimal open-source AI coding agent built from roughly 100 lines of Python that only uses bash (no tool-calling APIs) yet scores over 74% on SWE-bench Verified. Created by the Princeton/Stanford team behind SWE-bench and SWE-agent, it supports local, Docker, and sandboxed execution and is used internally by companies like Meta, NVIDIA, and IBM.
What it can do
Autonomously resolve software engineering tasks using bash commands
Coding task/issue description → Code changes/patch
Execute agent workflows in local, Docker, or sandboxed environments
Execution environment configuration → Isolated task execution
Interact with a coding environment using only bash commands without tool-calling APIs
Bash commands → Command execution results
Why it made the leaderboard
It shows a coding agent needs nothing more than a bash loop to reach state-of-the-art SWE-bench results, giving builders a readable ~100-line baseline they can fork, benchmark, and run locally, in Docker, or sandboxed against any LLM via litellm.
Tags
Tech Stack
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.