SWE-agent is an autonomous AI system that enables language models to resolve GitHub issues by navigating repositories, editing files, and running shell commands in a sandboxed Docker environment.
It is designed as a research-oriented platform for autonomous software engineering and cybersecurity tasks.
- 01
Autonomous GitHub issue resolution
- 02
Agent-Computer Interface (ACI) for repository navigation
- 03
Sandboxed Docker execution environment
- 04
Support for multiple LLM backends including GPT-4o and Claude
- 05
EnIGMA mode for offensive cybersecurity and CTF challenges
Open Source
Free and open-source under the MIT license; users are responsible for their own LLM API costs and infrastructure.
Best for
Researchers and developers needing a transparent, hackable platform for autonomous program repair, benchmarking, or cybersecurity research.
Not ideal for
Teams requiring a managed, supported product with a GUI, or users seeking an actively maintained tool for production workflows.
A powerful, research-grade tool that has been superseded by mini-swe-agent; use it only if you specifically need to study its architecture or require the legacy EnIGMA mode.
The project is currently in maintenance mode, with development effort shifted to mini-swe-agent, which offers similar performance with significantly reduced complexity.
As of
Is SWE-agent free?+
Yes - SWE-agent is Open Source. Free and open-source under the MIT license; users are responsible for their own LLM API costs and infrastructure.
Is SWE-agent open source?+
Yes - SWE-agent is open source. Free and open-source under the MIT license; users are responsible for their own LLM API costs and infrastructure.
Who is SWE-agent best for?+
Researchers and developers needing a transparent, hackable platform for autonomous program repair, benchmarking, or cybersecurity research.
Who is SWE-agent not ideal for?+
Teams requiring a managed, supported product with a GUI, or users seeking an actively maintained tool for production workflows.
What are the best SWE-agent alternatives?+
The closest SWE-agent alternatives on ai.dosa.dev are Jules, OpenHands, Sweep - all listed under Autonomous & Async Agents.
Who makes SWE-agent?+
SWE-agent is developed by Princeton NLP. 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.