LLM inference engine for AMD RDNA4 — Rust + Vulkan compute shaders, gguf & native FP8.
GitHub repository with 9 stars and 1 forks.
Language: Rust
Topics: fp8, gguf, inference, llm, rust, vulkan, amd, gfx1201, machine-learning, rdna4
2026-06-05: 9 stars and 1 forks.
An enhanced tool for CodexApp, striving to make Codex better to use and more comfortable 一个CodexApp的增强工具，努力让Codex变得更好用更舒服
GitHub repository with 13,659 stars and 844 forks.
Trending score: 5.16; stars gained: +916; forks gained: +44.
Language: Rust
DeepSeek + MiMo coding agent in terminal
GitHub repository with 37,102 stars and 3,192 forks.
Trending score: 4.80; stars gained: +393; forks gained: +32.
Language: Rust
Topics: cli, deepseek, llm, rust, terminal, tui
Lightweight coding agent that runs in your terminal
GitHub repository with 88,779 stars and 13,042 forks.
Trending score: 4.58; stars gained: +326; forks gained: +48.
Language: Rust
Your Personal AI super intelligence. Private, Simple and extremely powerful.
GitHub repository with 30,803 stars and 2,971 forks.
Trending score: 4.37; stars gained: +332; forks gained: +50.
Language: Rust
Codebase intelligence for TypeScript and JavaScript. Free static layer: unused code, duplication, circular deps, complexity hotspots, architecture boundaries. Optional paid runtime layer: hot-path review and cold-path deletion evidence from real production traffic. Rust-native, sub-second, zero-config framework support.
GitHub repository with 3,040 stars and 91 forks.
Trending score: 4.05; stars gained: +346; forks gained: +16.
Language: Rust
Topics: cli, code-quality, dead-code, developer-tools, javascript, linter
agent multiplexer that lives in your terminal.
GitHub repository with 4,330 stars and 264 forks.
Trending score: 4.04; stars gained: +212; forks gained: +3.
Language: Rust
Topics: agent, agent-orchestration, ai, ai-agents, claude-code, cli
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.
GitHub repository with 3,377 stars and 739 forks.
Trending score: 1.10; stars gained: +1; forks gained: +3.
Language: Python
Topics: cuda, deep-learning, fp4, fp8, gpu, jax
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
GitHub repository with 840 stars and 177 forks.
Trending score: 0.69; stars gained: +4; forks gained: +2.
Language: Python
Topics: attention, blackwell, cuda, cuda-kernels, cuda-toolkit, deep-learning
Lynn 原生 LLM 推理引擎 · W4A8/NVFP4 量化 · 自写 CUDA/Triton kernel · MoE · 投机解码 | Lynn-native LLM inference engine for NVIDIA Blackwell
GitHub repository with 17 stars and 0 forks.
Trending score: 0.05; stars gained: +0; forks gained: +0.
Language: Python
Topics: ai-inference, blackwell, cuda, deep-learning, fp8, gpu