Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/swe-agent/mini-swe-agent/llms.txt

Use this file to discover all available pages before exploring further.

mini-swe-agent is a ~100-line Python agent that solves real software engineering tasks using only bash. This guide walks you through installing the package, connecting it to a model provider, and running your first prompt — from zero to working agent in under five minutes.
1

Install mini-swe-agent

Choose the installation method that fits your workflow. pip is the simplest option; uv/uvx and pipx keep the package isolated from your system Python; and from source is best if you want to customize or contribute.
pip install mini-swe-agent
If you installed with pipx and mini is not found immediately, run pipx ensurepath and open a new shell.
2

Configure your model

Run the interactive setup wizard to choose a model provider and set your API key. This wizard runs automatically the first time you launch mini; if you skipped it, run it directly:
mini-extra config setup
The wizard stores your settings in mini’s global config file so you never have to set them again. See Model setup and configuration for manual setup and a full list of supported providers.
3

Run the agent

Launch the interactive CLI and give it your first task:
mini
The agent opens an interactive session. Type a prompt and press Enter to start. You can also pass a prompt directly on the command line:
mini "Help me document & type my codebase by adding short docstrings and type hints."

​
Example prompts to try

Copy any of these into the mini prompt to see what the agent can do:
  • Build something new — Implement a Sudoku solver in Python in the sudoku folder. Make sure the codebase is modular and well tested with pytest.
  • Fix failing tests — Please run pytest on the current project, discover failing unit tests and help me fix them. Always make sure to test the final solution.
  • Improve code quality — Help me document & type my codebase by adding short docstrings and type hints.

​
Next steps

Once you have the agent running, explore these topics:
Upgrading from v1? Check the v2 migration guide for a full list of breaking changes and how to update your config files and Python code.

Build docs developers (and LLMs) love

Get started for freeTalk to us