1.facebookresearch / swe-sweepHow many bugs can LMs find & fix in large codebases?aiai-agentsbenchmarkbenchmarkingharborharbor-framework+5 morePythonOther license217 total25 forks+19 starsfrom 196 · score 3.00
2.locustio / locustWrite scalable load tests in plain Python 🚗💨locustpythonload-testingperformance-testinghttpbenchmarking+5 morePythonMIT28K total3.3K forks+14 starsfrom 28,240 · score 2.71