Swe Agent
Autonomous LM agent that automatically resolves GitHub issues via a custom ACI
Visit Swe AgentAbout Swe Agent
SWE-agent is an open-source autonomous software engineering agent developed by researchers at Princeton University and Stanford University that turns large language models (e.g. GPT-4) into agents capable of automatically fixing issues in real GitHub repositories. It uses a custom Agent-Computer Interface (ACI) that provides LM-friendly commands and feedback for browsing codebases, editing files, and executing tests. The tool also supports offensive cybersecurity and competitive coding challenges. It is now in maintenance-only mode, superseded by mini-swe-agent.
Latest News about Swe Agent
Orchard: An open framework for scalable agentic AI
Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure:
Cohere North Mini Code open-source coding agent
Cohere's North Mini Code ranks 8th of 127 open-weight models on output speed — but generates 3x the output tokens of comparable models in independent testing.
Best AI Agents for Software Development Ranked: A Benchmark-Driven Look at the Current Field
The AI coding agent field in 2026 is more capable, more fragmented, and harder to benchmark than it looks. Claude Code leads on code quality at 87.6% SWE-bench Verified. GPT-5.5 tops Terminal-Bench at 82.7%. But the benchmark OpenAI itself declared contaminated in February 2026 is still being used to rank these tools — including by the labs publishing their own scores.
Resources
Product Website
Visit Swe Agent's official website for product details and getting started.