ScalingIntelligence/KernelBench

KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)

benchmarkcodegenevaluationgpurl-environmenttooling

License & maintenance

Custom or modified license that GitHub does not recognise: read the LICENSE file in the repository before using it in a product.

Last code push 6 months ago.

	Repository	Stars	Language	License	Activity
1	AntonOsika/gpt-engineerCLI platform to experiment with codegen. Precursor to: https://lovable.dev	★ 55k	Python	MIT	Archived
2	langfuse/langfuse🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.	★ 36k	TypeScript	Other	Active
3	Tencent/WeKnoraOpen-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.	★ 34.6k	Go	Other	Active
4	mlflow/mlflowThe open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and	★ 28.4k	Python	Apache-2.0	Active
5	promptfoo/promptfooTest your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepS	★ 26.1k	TypeScript	MIT	Active
6	comet-ml/opikDebug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, an	★ 22.7k	Python	Apache-2.0	Active
7	morluto/reaReverse engineer anything with agents, from app behavior down to native binaries.	★ 319.5k	TypeScript	MIT	Active
8	mattpocock/skillsSkills for Real Engineers. Straight from my .agents directory.	★ 296k	Shell	MIT	Active