mini-swe-agent
A lightweight AI agent for resolving GitHub issues or providing help in the command line.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 4.9k
- Source
- GitHub
- Added
- 2026-06-04
- Last verified
- 2026-06-04
Overview
mini-swe-agent is a concise AI agent that resolves GitHub issues or assists in the command line with just 100 lines of code. It requires no complex configuration or large codebase, yet achieves over 74% score on the SWE-bench evaluation benchmark. Ideal for developers and teams needing quick problem resolution.
Key features
- ▪Simple and efficient, only 100 lines of code
- ▪Supports deployment across multiple environments
- ▪Compatible with various model interfaces
- ▪Excellent performance, fast startup
Use cases
Pros
- ＋Easy to use
- ＋High performance
- ＋Wide compatibility
- ＋Fast startup
Limitations / notes
- －Relatively limited functionality
- －Dependent on bash tools
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 models does mini-swe-agent support?
Supports all models via interfaces such as litellm, openrouter, portkey.
How do I use mini-swe-agent?
It can be run in the command line and supports deployment across various environments.
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.