Minimal, zero-dependency LLM inference in pure C11. CPU-first with NEON/AVX2 SIMD. Flash MoE (pread + LRU expert cache). TurboQuant 3-bit KV compression (8.9x less memory per session). 20+ GGUF quant formats. Compiles to WASM.
GitHub repository with 20 stars and 7 forks.
Language: C
Topics: avx2, c, cpu-inference, gguf, inference, kv-cache, llm, moe, neon, quantization
Trending score 0.05, activity score 0.05, stars gained +0, forks gained +0.
2026-06-05: 20 stars and 7 forks.
Minimal, zero-dependency LLM inference in pure C11. CPU-first with NEON/AVX2 SIMD. Flash MoE (pread + LRU expert cache). TurboQuant 3-bit KV compression (8.9x less memory per session). 20+ GGUF quant formats. Compiles to WASM.
GitHub repository with 20 stars and 7 forks.
Trending score: 0.05; stars gained: +0; forks gained: +0.
Language: C
Topics: avx2, c, cpu-inference, gguf, inference, kv-cache
DeepSeek 4 Flash local inference engine for Metal and CUDA
GitHub repository with 12,977 stars and 1,130 forks.
Trending score: 3.46; stars gained: +74; forks gained: +5.
Language: C
The fastest path to AI-powered full stack observability, even for lean teams.
GitHub repository with 79,065 stars and 6,456 forks.
Trending score: 3.03; stars gained: +25; forks gained: +4.
Language: C
Topics: ai, alerting, cncf, data-visualization, database, devops
The programming language for agents
GitHub repository with 4,874 stars and 315 forks.
Trending score: 2.75; stars gained: +27; forks gained: +4.
Language: C
ESP32 desk dashboard that shows Claude Code usage
GitHub repository with 1,531 stars and 182 forks.
Trending score: 2.63; stars gained: +24; forks gained: +5.
Language: C
Recent CVE PoC & reproduction scripts. Focused on high-severity vulnerabilities across Linux kernel, Windows, macOS and more.
GitHub repository with 490 stars and 84 forks.
Trending score: 2.27; stars gained: +20; forks gained: +2.
Language: C
Topics: c, cybersecurity, linux, poc, python, python3
Zero instrucment system-level AI agent tracing in eBPF
GitHub repository with 408 stars and 59 forks.
Trending score: 2.26; stars gained: +23; forks gained: +2.
Language: C
Topics: agent, ebpf, llm, observability
Performance-portable, length-agnostic SIMD with runtime dispatch
GitHub repository with 5,596 stars and 438 forks.
Trending score: 0.63; stars gained: +2; forks gained: +0.
Language: C++
Topics: avx, avx-512, avx-instructions, avx2, avx512, intrinsics
Fast inference engine for Transformer models
GitHub repository with 4,509 stars and 492 forks.
Trending score: 0.51; stars gained: +2; forks gained: +0.
Language: C++
Topics: neural-machine-translation, cpp, mkl, quantization, cuda, thrust
DirectXMath is an all inline SIMD C++ linear algebra library for use in games and graphics apps
GitHub repository with 1,778 stars and 257 forks.
Trending score: 0.37; stars gained: +1; forks gained: +0.
Language: C++
Topics: microsoft, directx, simd, neon, cpp-library, sse
Minimal, zero-dependency LLM inference in pure C11. CPU-first with NEON/AVX2 SIMD. Flash MoE (pread + LRU expert cache). TurboQuant 3-bit KV compression (8.9x less memory per session). 20+ GGUF quant formats. Compiles to WASM.
GitHub repository with 20 stars and 7 forks.
Trending score: 0.05; stars gained: +0; forks gained: +0.
Language: C
Topics: avx2, c, cpu-inference, gguf, inference, kv-cache
Parsing gigabytes of JSON per second : used by Facebook/Meta Velox, the Node.js runtime, ClickHouse, WatermelonDB, Apache Doris, Milvus, StarRocks
GitHub repository with 23,798 stars and 1,257 forks.
Trending score: 0.04; stars gained: +0; forks gained: +0.
Language: C++
Topics: json, json-parser, simd, avx2, sse42, neon
Cache-aware frequency sort: a header-only C++20 sort for low-cardinality integer arrays on x86-64.
GitHub repository with 21 stars and 0 forks.
Trending score: 0.01; stars gained: +0; forks gained: +0.
Language: C++
Topics: avx2, benchmark, branchless, cache-aware, cpp, cpp20