SWE-agent
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]
SWE-agent scores 6.5/10 (Solid) in Agents.
Language Python License MIT Stars 19.7k★ Type heavyweight Self-host Yes Repo SWE-agent/SWE-agent Homepage https://swe-agent.com/
Quality
Solid 6.5
Adoption 57
Activity 60
Maturity 92
Community 59
Capability 34
Show the math
Overall 6.5/10
value = 6.5/10
score = value
Adoption 6.2/10
value = 57.4/100
score = 1 + 9 * value / 100
Activity 6.4/10
value = 59.9/100
score = 1 + 9 * value / 100
Maturity 9.3/10
value = 92.1/100
score = 1 + 9 * value / 100
Community 6.3/10
value = 58.9/100
score = 1 + 9 * value / 100
Capability 4/10
value = 33.8/100
score = 1 + 9 * value / 100
Key metrics
19.7k★ GitHub stars
18/90d Recent commits
7 devs/90d Recent contributors
SWE 34% SWE-bench Verified SWE-agent 1.0 + Claude 3.7; mini-SWE-agent reaches ~74% with frontier models
2.3y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
- Heavyweight
Heavyweight
Resource-heavy to run (GPU, large memory, or multi-service stack).
swe-bench autonomous research github-issues agentic coding-agent