The 100 line AI agent that's actually useful

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

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

mini is for

Researchers who want to benchmark, fine-tune or RL without assumptions, bloat, or surprises
💻 Developers who like their tools like their scripts: short, sharp, and readable
Engineers who want something trivial to sandbox & to deploy anywhere

Here's some details:

Minimal: Just 100 lines of python (+100 total for env, model, script) — no fancy dependencies!
Powerful: Resolves 65% of GitHub issues in the SWE-bench verified benchmark.
Convenient: Comes with UIs that turn this into your daily dev swiss army knife!
Deployable: In addition to local envs, you can use docker, podman, singularity, apptainer, and more
Cutting edge: Built by the Princeton & Stanford team behind SWE-bench and SWE-agent.

Why use mini-SWE-agent for research?

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, a lot of this is not needed at all to build a useful agent!

In fact, mini-SWE-agent:

Does not have any tools other than bash — it doesn't even use the tool-calling interface of the LMs. This means that you can run it with literally any model. When running in sandboxed environments you also don't need to take care of installing a single package — all it needs is bash.
Has a completely linear history — every step of the agent just appends to the messages and that's it. So there's no difference between the trajectory and the messages that you pass on to the LM. Great for debugging & fine-tuning.
Executes actions with subprocess.run — every action is completely independent (as opposed to keeping a stateful shell session running). This makes it trivial to execute the actions in sandboxes (literally just switch out subprocess.run with docker exec) and to scale up effortlessly. Seriously, this is a big deal, trust me.

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.

Why use mini-SWE-agent as a tool?

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

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

Simple enough to understand at a glance
Convenient enough to use in daily workflows
Flexible to extend

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

Does not have any tools other than bash — it doesn't even use the tool-calling interface of the LMs. Instead of implementing custom tools for every specific thing the agent might want to do, the focus is fully on the LM utilizing the shell to its full potential. Want it to do something specific like opening a PR? Just tell the LM to figure it out rather than spending time to implement it in the agent.
Executes actions with subprocess.run — every action is completely independent (as opposed to keeping a stateful shell session running). This is a big deal for the stability of the agent, trust me.
Has a completely linear history — every step of the agent just appends to the messages that are passed to the LM in the next step and that's it. This is great for debugging and understanding what the LM is prompted with.

Should I use mini-SWE-agent or swe-agent?

You should use mini-swe-agent if

You want a quick command line tool that works locally
You want an agent with a very simple control flow
You want even faster, simpler & more stable sandboxing & benchmark evaluations
You are doing FT or RL and don't want to overfit to a specific agent scaffold

You should use swe-agent if

You need specific tools or want to experiment with different tools
You want to experiment with different history processors
You want very powerful yaml configuration without touching code

What you get with both

Excellent performance on SWE-Bench
A trajectory browser

Simple UI (`mini`)	Visual UI (`mini -v`)

Batch inference	Trajectory browser

Python bindings	More in the docs
`agent = DefaultAgent( LitellmModel(model_name=...), LocalEnvironment(), ) agent.run("Write a sudoku game")`	Quick start `mini` FAQ Configuration Power up