SWE-agent

ai-agentStable

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

About SWE-agent

SWE-agent enables your language model of choice (e.g. GPT-4o or Claude Sonnet 4) to autonomously use tools to fix issues in real GitHub repositories, find cybersecurity vulnerabilities, or perform any custom task. SWE-agent is built and maintained by researchers from Princeton University and Stanford University. [SWE-agent: EnIGMA][enigma] is a mode for solving offensive cybersecurity (capture the flag) challenges. EnIGMA achieves state-of-the-art results on multiple cybersecurity benchmarks (see leaderboard). Please use SWE-agent 0.7 while we…

Read the full README on GitHub →

SWE-agent growth signals this week

• Gained 68 stars in the last 7 days
• 17x the median weekly star growth of its category

Growth score: 32/100 week of 2026-07-20

Signal history

SWE-agent alternatives

Projects in the same category, closest in size — picked by data, not opinion.

See all ai-agent projects ranked by growth →

Frequently asked questions

Is SWE-agent still maintained?

Yes — actively maintained. The last push was on 2026-07-16, with 101 contributors.

Is SWE-agent growing?

It is stable this week, with a growth score of 32/100. See the weekly history above.

What are the best SWE-agent alternatives?

Closest by category and size in our data: Suna, devika, localGPT — full list with live signals above.

Topics

Embed this badge

Show your project's live signal in your README — it updates weekly with the data.

Tracked since 2026-06-10 · data as of 2026-07-19 · 43 open issues · 10 releases