SWE-agent is a system designed to turn language models into autonomous software engineering agents capable of fixing issues in GitHub repositories.
Follow SWE-agent to get an email when its listing changes, such as new pricing or features. One digest a day at most, and you can unsubscribe anytime.
It utilizes a custom Agent-Computer Interface (ACI) to provide language models with a streamlined, interactive way to navigate, view, edit, and execute code within a environment.
- 01
Agent-Computer Interface (ACI) for efficient file navigation and editing
- 02
Integration with litellm to support a wide range of language models
- 03
Massively parallel code execution via SWE-ReX
- 04
Configurable retry mechanisms and tool bundles
- 05
Support for multimodal models to process images from issues
Open Source
The tool is available as open-source software; users are responsible for the costs associated with the language model APIs used for execution.
Best for
Autonomous resolution of software engineering issues in real GitHub repositories and performing custom developer tasks using language models.
Not ideal for
Simple tasks that do not require autonomous repository navigation or complex environment interaction, or users seeking an actively developed flagship tool (it has been superseded by mini-swe-agent).
While historically significant for introducing the Agent-Computer Interface, SWE-agent has been superseded by mini-swe-agent, which offers similar performance with a simpler and more flexible architecture.
The project is currently in maintenance-only mode following the release of version 1.1.0 on May 22, 2025, which added support for SWE-smith and multilingual evaluation.
As of
Is SWE-agent free?+
Yes - SWE-agent is Open Source. The tool is available as open-source software; users are responsible for the costs associated with the language model APIs used for execution.
Is SWE-agent open source?+
Yes - SWE-agent is open source. The tool is available as open-source software; users are responsible for the costs associated with the language model APIs used for execution.
Who is SWE-agent best for?+
Autonomous resolution of software engineering issues in real GitHub repositories and performing custom developer tasks using language models.
Who is SWE-agent not ideal for?+
Simple tasks that do not require autonomous repository navigation or complex environment interaction, or users seeking an actively developed flagship tool (it has been superseded by mini-swe-agent).
What are the best SWE-agent alternatives?+
The closest SWE-agent alternatives on ai.dosa.dev are Jules by Google, OpenHands, mini-swe-agent - all listed under Autonomous & Async Agents.
Who makes SWE-agent?+
SWE-agent is developed by Princeton University (in collaboration with Stanford University). It is listed in the Autonomous & Async Agents category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.