SWE-agent
| Field | Value |
|---|---|
| Developer | Princeton NLP |
| Language | Python |
| License | MIT |
| GitHub | SWE-agent/SWE-agent |
| Stars | 15K+ |
Overview
Section titled “Overview”SWE-agent is a research framework from Princeton NLP that enables LLMs to autonomously fix real GitHub issues. It achieved the first open-source SOTA on SWE-bench by providing LLMs with a custom Agent-Computer Interface (ACI) — specialized commands for navigating, searching, and editing codebases.
Key Features
Section titled “Key Features”- Agent-Computer Interface (ACI) — Custom shell commands optimized for LLM code editing
- SWE-bench SOTA — Proven on real-world GitHub issues at scale
- Configurable agents — YAML-based agent configuration
- Multi-model — Works with GPT-4o, Claude Sonnet, and other models
- Docker sandboxing — Safe execution environment for each issue
When to Use
Section titled “When to Use”✅ Autonomous GitHub issue fixing ✅ SWE-bench evaluation and research ✅ Building agents that work on unfamiliar codebases
❌ Interactive development (use AdaL CLI or Aider)