The 100 line AI agent that solves GitHub issues & more
In 2024, SWE-bench & SWE-agent helped kickstart the agentic AI for software revolution.
We now ask: What if SWE-agent was 100x smaller, and still worked nearly as well?
micro is for
- 🧪 Researchers who want to benchmark, fine-tune or RL without assumptions, bloat, or surprises
- 🧑💻 Hackers & power users 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.
- 🤗 Friendly: Comes with two convenient UIs that will turn this into your daily dev swiss army knife!
- 🍀 Environments: In addition to local envs, you can use docker, podman, singularity, apptainer, and more
- 🧪 Tested:
- 🎓 Cutting edge: Built by the Princeton & Stanford team behind SWE-bench and SWE-agent.
More motivation (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, as LMs have become more capable, a lot of this is not needed at all to build a useful agent! In fact, micro-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 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.
- 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 outsubprocess.runwithdocker exec) and to scale up effortlessly.
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.
More motivation (as a tool)
Some agents are overfitted research artifacts. Others are UI-heavy tools, highly optimized for a specific user experience. Both variants are hard to understand.
micro strives to be
- Simple enough to understand at a glance
- Convenient enough to use in daily workflows
- Flexible to extend
A hackable tool, not a black box.
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.
- Has a completely linear history — every step of the agent just appends to the messages and that's it.
- Executes actions with
subprocess.run— every action is completely independent (as opposed to keeping a stateful shell session running).
Should I use SWE-agent or micro-SWE-agent?
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
You should use micro-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
What you get with both
- Excellent performance on SWE-Bench
- A trajectory browser
Simple UI (micro)
|
Visual UI (micro -v)
|
|
|
|
| Batch inference | Trajectory browser |
|
|
|
| Python bindings | More in the docs |
agent = DefaultAgent(
LitellmModel(model_name=...),
LocalEnvironment(),
)
agent.run("Write a sudoku game")
|
🔥 Let's get started!
Install + run in virtual environment
pip install pipx && pipx ensurepath && pipx run micro-swe-agent [-v]
Alternative: Install in current environment
pip install micro-swe-agent && micro [-v]
Alternative: Install from source
git clone https://github.com/SWE-agent/micro-swe-agent.git
cd micro-swe-agent
pip install -e .
micro [-v]
Read more in our documentation:
- Quick start guide
- More on
microandmicro -v - Configuration
- Power up with the cookbook
- FAQ
- Contribute!
👀 More agentic AI
1 maintainer
Metadata
1 maintainer
Release files for micro-swe-agent 1.0.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| micro_swe_agent-1.0.2.tar.gz | 37.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| micro_swe_agent-1.0.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 89.6 kB
Release files / micro_swe_agent-1.0.2.tar.gz
| Download URL | micro_swe_agent-1.0.2.tar.gz |
|---|---|
| Size | 37.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7066b3a4d6fce57af583c6d31df727a32136690ea1647d16d66bfa785d54f4ad
|
|
BLAKE2b-256 checksum How to use checksums |
1a1922adbc2e750e5c75a1eaa233a27e6b6e8ffe4e6f5a96ae3c515d90203ca2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
Release files / micro_swe_agent-1.0.2-py3-none-any.whl
| Download URL | micro_swe_agent-1.0.2-py3-none-any.whl |
|---|---|
| Size | 52.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6c551b53f7d3641ec190611e3b10c5a3ac72598f67b1db2571f96a6345265e8a
|
|
BLAKE2b-256 checksum How to use checksums |
dbada2cf8fee7ac4fac711d3e66b4144ba5c99b2460a77f528adaf623e25f36f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
