← Developers
Open on GitHub 
#685 4
Kilian Lieret
@klieret · USA
25.3k
Weighted score
2.73k
Contributions
6
Repos
Top repos
- SWE-agent/SWE-agent
- SWE-agent/mini-swe-agent
- SWE-agent/SWE-ReX
- SWE-bench/SWE-bench
- facebookresearch/ProgramBench
- SWE-bench/SWE-smith
Ranked AI repos6
1946302
SWE-agent/SWE-agent
+4
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]
20.5k· Python· Applications
570115
SWE-agent/mini-swe-agent
+24
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
8.36k· Python· Applications
29631045
SWE-bench/SWE-bench
+2
SWE-bench: Can Language Models Resolve Real-world Github Issues?
6.00k· Python· AI Engineering
3556400
facebookresearch/ProgramBench
+2
Can Language Models Rebuild Programs From Scratch?
950· Python· AI Engineering
126749700
SWE-bench/SWE-smith
+0
[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
798· Python· Model Development
148788184
SWE-agent/SWE-ReX
+0
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
618· Python· Infrastructure