Skip to main content
AgentAI for Codev0.7

SWE-agent

by Princeton NLP · open-source · Last verified 2026-03-17

Princeton NLP's research agent that turns LLMs into autonomous software engineers. Achieves state-of-the-art results on SWE-bench by providing an agent-computer interface optimized for code navigation and editing.

https://swe-agent.com
B
BAbove Average
Adoption: BQuality: AFreshness: ACitations: A+Engagement: F

Specifications

License
MIT
Pricing
open-source
Capabilities
autonomous-coding, bug-fixing, codebase-navigation, patch-generation, test-validation
Integrations
github, docker, openai, anthropic
Use Cases
bug-fixing, research, benchmark-evaluation, automated-patching, code-repair
API Available
No
Autonomy Level
fully-autonomous
Tools Used
bash, file-editor, code-search, git
Skills
bug-fixing, code-navigation, patch-generation
Trust Score
78
Tags
coding-agent, research, open-source, princeton, benchmark
Added
2026-03-17
Completeness
95%

Index Score

66.7
Adoption
68
Quality
85
Freshness
82
Citations
90
Engagement
0

Explore the full AI ecosystem on Agents as a Service