What it does
mini-swe-agent is an AI agent that works on code by running commands in a terminal. Its makers, the team behind the SWE-bench test and SWE-agent, built it to be as simple as possible: the core is about 100 lines of Python.
It has no special tools beyond the command line, so it can work with almost any AI model. Its makers say it still scores well on SWE-bench, a common test of how well AI fixes real software bugs.
Researchers use it as a simple baseline for comparing AI models, and developers can use it day to day or as a starting point for their own agent.
Who it's for
Developers who want a lightweight coding agent, and researchers who need a simple, transparent agent for tests.
Can I use it without coding?
With some setup. You install it with Python's package tools and run it in a terminal. New to this? Start here.
Can I run it?
- Cost
- Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
- Computer
- An ordinary computer is fine
- API key
- Needed. An API key is a password-like code from an online AI service. What's that?
Try it
- Install it with Python's package installer.
- Run the mini command in your terminal and connect an AI model, following its quick-start guide.
- Describe the coding task you want it to do.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- Keep your API key private. Never paste it into websites or share it, and set a spending limit with the AI service.
- More on staying safe
Where people are talking about it
- SWE-agent paperResearch paper · May 2024