1.antirez / ds4DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCmCMIT24K total2.4K forks+21,486 starsfrom 2,746 · score 9.98
2.karpathy / llama2.cInference Llama 2 in one file of pure CCMIT20K total2.7K forks+884 starsfrom 19,368 · score 6.79
3.eunomia-bpf / agentsightlightweight system-level observability for AI AgentsagentebpfllmobservabilityCMIT771 total118 forks+460 starsfrom 311 · score 6.13