Skip to content

Installation from source

Installation from source is the preferred way to set up SWE-agent on your machine.

  1. Clone the repository, for example with 
    git clone https://github.com/SWE-agent/SWE-agent.git
  2. Run 
    python -m pip install --upgrade pip && pip install --editable .
    at the repository root (as with any python setup, it's recommended to use conda or virtual environments to manage dependencies).
  3. Set up your language model of choice as explained here.

Let's run a quick check:

sweagent --help

should show an overview over the available top-level commands.

Command not found? You might also try `python -m sweagent`. If this also doesn't work, please check with `which python` that you're using the same `python` as when you installed SWE-agent.

Optional installation steps:

  1. The default backend for SWE-agent is docker, so we recommend to install Docker (follow the docs or use the get-docker.sh script for linux), then start Docker locally. Problems? See docker issues. If you do not want to use docker, you can still use SWE-agent with code evaluation in the cloud.
  2. If you plan on using the web-based GUI: Install nodejs.

Installation tips

  • If you run into docker issues, see the installation tips section for more help.
  • SWE-agent is still in active development. Features and enhancement are added often. To make sure you are on the latest version, periodically run git pull (there is no need to redo the pip install).
  • SWE-agent EnIGMA is currently only compatible with v0.7 of SWE-agent. Please run git switch v0.7 after step 1 to switch to the correct version.
  • Want to modify SWE-agent? Great! There are a few extra steps and tips: Please check our contribution guide.