SWE-agent/SWE-agent
An autonomous AI agent that uses LLMs to automatically fix GitHub issues, find cybersecurity vulnerabilities, and solve coding challenges.
Velocity · 7d
+6.7
★ / day
Trend
→steady
star history
SWE-agent is a research-built agent framework that takes GitHub issues as input and uses a language model of choice to autonomously navigate repositories, read code, write patches, and submit fixes. It achieved state-of-the-art performance on SWE-bench among open-source projects and can be configured via YAML for various tasks including offensive security and competitive coding.
Frequently asked
- What is SWE-agent/SWE-agent?
- An autonomous AI agent that uses LLMs to automatically fix GitHub issues, find cybersecurity vulnerabilities, and solve coding challenges.
- Is SWE-agent open source?
- Yes — SWE-agent/SWE-agent is open source, released under the MIT license.
- What language is SWE-agent written in?
- SWE-agent/SWE-agent is primarily written in Python.
- How popular is SWE-agent?
- SWE-agent/SWE-agent has 20.1k stars on GitHub and is currently holding steady.
- Where can I find SWE-agent?
- SWE-agent/SWE-agent is on GitHub at https://github.com/SWE-agent/SWE-agent.