📣 mini-swe-agent now powers Ramp SWE-Bench

📣 mini-swe-agent beats Claude Code and Codex on DeepSWE

📣 Run mini-swe-agent on our new & extremely challenging benchmark, ProgramBench

📣 New tutorial on building minimal AI agents

This is mini-swe-agent v2. Read the migration guide. For the previous version, check out the v1 branch.

In 2024, we built SWE-bench & SWE-agent and helped kickstart the coding agent revolution.

We now ask: What if our agent was 100x simpler, and still worked nearly as well?

SWE-agent jump-started the development of AI agents in 2024. Back then, we placed a lot of emphasis on tools and special interfaces for the agent. However, one year later, as LMs have become more capable, a lot of this is not needed at all to build a useful agent! In fact, the mini agent

This makes it perfect as a baseline system and for a system that puts the language model (rather than the agent scaffold) in the middle of our attention. You can see the result on the SWE-bench (bash only) leaderboard, that evaluates the performance of different LMs with mini.

Some agents are overfitted research artifacts. Others are UI-heavy frontend monsters.

The mini agent wants to be a hackable tool, not a black box.

Unlike other agents (including our own swe-agent), it is radically simpler, because it:

You should consider mini-swe-agent your default choice. In particular, you should use mini-swe-agent if

agent = DefaultAgent( LitellmModel(model_name=...), LocalEnvironment(), ) agent.run("Write a sudoku game")

Let's get started!

Option 1: If you just want to try out the CLI (package installed in anonymous virtual environment)

pip install uv && uvx mini-swe-agent

or

pip install pipx && pipx ensurepath && pipx run mini-swe-agent

Option 2: Install CLI & python bindings in current environment

pip install mini-swe-agent mini # run the CLI

Option 3: Install from source (developer setup)

If you found this work helpful, please consider citing the SWE-agent paper in your work:

@inproceedings{yang2024sweagent, title={{SWE}-agent: Agent-Computer Interfaces Enable Automated Software Engineering}, author={John Yang and Carlos E Jimenez and Alexander Wettig and Kilian Lieret and Shunyu Yao and Karthik R Narasimhan and Ofir Press}, booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems}, year={2024}, url={https://arxiv.org/abs/2405.15793} }

Our other projects: