Overview
SWE-agent is a software engineering agent that takes a GitHub issue, lets an LLM inspect and modify a repository with tools, and attempts to produce a validated fix, with strong use in SWE-bench research workflows.
Features and best fit
Based on official documentation; not hands-on tested · Content checked:
Let an agent inspect, edit, and validate a repository from an issue
The LLM can use shell and editing tools to move from issue understanding through code changes and validation.
Configure behavior in YAML and apply it to benchmarks
Agent behavior can be configured and reused across SWE-bench and custom coding tasks.
For research, evaluation, and reproducible experiments with coding agents
It is useful for studying how agent interfaces, tools, and prompts affect performance on real repositories.
Sources: [2]
Compare mini-SWE-agent for any new adoption
The README says most active development moved to mini-SWE-agent and recommends it going forward. Treat SWE-agent as an important existing system and comparison point.
Sources: [2]
Official sources
- [1]SWE-agent/SWE-agent repository(2026-09-20)
- [2]SWE-agent README(2026-09-20)
- [3]SWE-agent documentation(2026-09-20)
- [4]SWE-agent MIT license(2026-09-20)
Supplemental curator note
SWE-agent is a prominent research agent for turning GitHub issues into repository-level fixes, but its README now states that most current development has moved to `mini-swe-agent` and recommends the newer project going forward. New evaluations should compare both.
Try it in 3 steps
- 1
Get the source
git clone --depth 1 https://github.com/SWE-agent/SWE-agent.git - 2
Enter the repository
cd SWE-agent - 3
Check the official steps
Continue with the commands in the README Installation, Quick Start, or Getting Started section.
find . -maxdepth 1 -iname 'README*' -exec sed -n '1,220p' {} \; -quit
Growth
Growth trends · Last 30 days
20,369 Stars
Trend data is still being collected.
Development activity
Last 90 days · weekly
- Commits (last 30 days)
- 0
- Open PRs
- 71
Development activity is still being collected.
Built with
Categories and tags
GitHub data
GitHub dataView detailed GitHub data
GitHub Topics
- agent
- ai
- developer-tools
- llm
- agent-based-model
- lms
- cybersecurity
- Stars
- 20,369
- Forks
- 2,230
- Watchers
- 112
- Open issues
- 45
- Contributors
- 97
- Primary language
- Python
- License
- MIT
- Repository last updated
- Sep 14, 2026
Related information
Write a related articleShare a guide or use case for this OSS in Markdown. Articles are published after administrator approval.
Explore next
- OpenClaw390,099 Stars
A persistent personal AI assistant platform spanning channels, tools, memory, and schedules.
TypeScript - React250,594 Stars
A JavaScript library for building web and native user interfaces from declarative components.
JavaScript - Hermes Agent247,156 Stars
A persistent AI agent with memory, skills, cron jobs, subagents, and multiple terminal backends.
Python - n8n205,375 Stars
A fair-code platform combining a visual canvas and code for service integrations, workflows, and AI agents.
TypeScript - TensorFlow200,194 Stars
An end-to-end machine-learning platform connecting research, training, evaluation, visualization, and deployment.
C++
Report incorrect information
Tell us if any listing information is incorrect or outdated.