SWE-agent
SWE-agent is an AI agent that automatically fixes GitHub issues and supports multiple language models.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 19.4k
- Source
- GitHub
- Added
- 2026-06-05
- Last verified
- 2026-06-05
Overview
SWE-agent is an AI agent capable of autonomously solving real-world issues in GitHub repositories, identifying security vulnerabilities, or performing custom tasks by leveraging various tools. Users can run SWE-agent by simply configuring a YAML file, making it suitable for researchers and developers.
Key features
- ▪Automatically fix GitHub issues
- ▪Supports multiple language models
- ▪Applicable to cybersecurity
- ▪Simple and configurable
Use cases
Pros
- ＋Leading performance in open-source projects
- ＋Highly configurable
- ＋Well-documented
- ＋Easy to research and modify
Limitations / notes
- －Primary development has shifted to mini-swe-agent
- －Recommended to use mini-swe-agent instead
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
What is the difference between SWE-agent and mini-swe-agent?
mini-swe-agent performs comparably to SWE-agent but is simpler. It is recommended to use mini-swe-agent.
How do I get started with SWE-agent?
You can try it online via GitHub Codespaces, or follow the official documentation for local installation.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.