This GitHub Action checks AI coding context files for security issues, structural problems, and anti-patterns.
Open source
24 alternativesSWE Agent
SWE-agent takes a GitHub issue and attempts to fix it using a language model.
About SWE Agent
SWE-agent is an open-source research project that enables a language model of your choice to autonomously use tools to fix issues in real GitHub repositories, or to perform custom tasks. It includes EnIGMA, a mode for offensive cybersecurity (capture-the-flag) challenges, and is configured through a single YAML file. The project is built and maintained by researchers from Princeton University and Stanford University and is designed to be simple and hackable.
Development effort has largely moved to mini-swe-agent, which the maintainers describe as superseding SWE-agent and which they recommend going forward. EnIGMA users are asked to use SWE-agent 0.7 while it is updated for 1.0. No pricing information is provided; SWE-agent is released under the MIT license.
Key features
- Lets a language model of your choice use tools autonomously
- Attempts to fix real GitHub issues in repositories
- EnIGMA mode for offensive cybersecurity and capture-the-flag challenges
- Configured through a single yaml file
- Reported state of the art on SWE-bench among open-source projects
- Supports custom tasks beyond issue fixing
Best for: Researchers and developers who want to study or build on an open-source language-model agent for automated software engineering and cybersecurity tasks.
Good for
- Open source under the MIT license, with documentation for installation, command-line use and SWE-bench benchmarking
- Built and maintained by researchers from Princeton University and Stanford University
- Designed to be simple and hackable for research, with free-flowing, generalizable behavior left to the language model
Watch out for
- Most current development effort is on mini-swe-agent, which maintainers say has superseded SWE-agent and which they recommend instead
- EnIGMA mode requires SWE-agent 0.7 while it is updated for version 1.0
- Users must supply their own language model; no pricing information is given
SWE Agent at a glance
- Category
- AI & Machine Learning › AI Coding Tools
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
SWE Agent alternatives
Tools and sites you could use instead, ranked by how closely they match.
The GPT Pilot repository describes an AI software development tool for software projects.
Use Open Interpreter as a coding agent with open language models for development work.
Open source
24 alternatives
OpenRabbit reviews GitHub pull requests through GitHub Actions, without requiring separate hosting.
FreeOpen source
24 alternatives
code2prompt converts a codebase into one language-model prompt with a source tree, templates, and token counts.
Open source
24 alternatives
Honey reduces token usage by giving AI coding agents a cross-tool skill for writing less code and prose.
Open source
24 alternativesPopular in AI Coding Tools
Well-known listings from the same topic.
LM Studiolmstudio.aiSampleApp.aisampleapp.aiCodeAnt AIcodeant.aiPoseTrackerposetracker.comOpenCodeopencode.aiRefact.airefact.ai
SWE Agent FAQ
Is SWE-agent still the recommended tool from this project?
Most current development effort is on mini-swe-agent, which the maintainers say has superseded SWE-agent and matches its performance while being much simpler. Their general recommendation is to use mini-swe-agent going forward.
Which version of SWE-agent should be used for the EnIGMA offensive cybersecurity mode?
Use SWE-agent 0.7 while EnIGMA is updated for version 1.0.
What license does SWE-agent use?
MIT; details are in the LICENSE file in the repository.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.