zolotukhin/zinc
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon
GitHub repository with 400 stars and 15 forks.
Language: Zig
Topics: amd, amdgpu, gpt, gpu, openai, pytorch, qwen3, rdna3, rdna4, transformer
Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon
GitHub repository with 400 stars and 15 forks.
Language: Zig
Topics: amd, amdgpu, gpt, gpu, openai, pytorch, qwen3, rdna3, rdna4, transformer
2026-06-05: 400 stars and 15 forks.
Build desktop + mobile apps with Zig and web UI
GitHub repository with 4,106 stars and 169 forks.
Trending score: 1.93; stars gained: +8; forks gained: +1.
Language: Zig
A cross-platform terminal workspace for remote development and AI agents, powered by libghostty-vt.
GitHub repository with 141 stars and 10 forks.
Trending score: 1.14; stars gained: +14; forks gained: +3.
Language: Zig
Topics: ghostty, terminal, windows, macos
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
GitHub repository with 135 stars and 8 forks.
Trending score: 1.00; stars gained: +8; forks gained: +2.
Language: Zig
Topics: agent, anthropic-api, apple-silicon, claude-code, inference, language-model
Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild
GitHub repository with 3,583 stars and 146 forks.
Trending score: 0.96; stars gained: +6; forks gained: +1.
Language: Zig
Topics: ai, bazel, hpc, inference, xla, zig
Session persistence for terminal processes
GitHub repository with 1,560 stars and 90 forks.
Trending score: 0.84; stars gained: +4; forks gained: +0.
Language: Zig
Topics: ghostty, tmux, zig, session-persistence
Drop-in replacement for `claude -p` that drives the interactive Claude Code TUI inside an in-process zmux PTY session.
GitHub repository with 364 stars and 28 forks.
Trending score: 0.64; stars gained: +4; forks gained: +0.
Language: Zig
A high-throughput and memory-efficient inference and serving engine for LLMs
GitHub repository with 82,001 stars and 17,690 forks.
Trending score: 3.75; stars gained: +79; forks gained: +46.
Language: Python
Topics: amd, blackwell, cuda, deepseek, deepseek-v3, gpt
Lightweight Armoury Crate alternative for Asus laptops with nearly the same functionality. Works with ROG Zephyrus, Flow, TUF, Strix, Scar, ProArt, Vivobook, Zenbook, Expertbook, ROG Ally, and many more.
GitHub repository with 13,525 stars and 506 forks.
Trending score: 2.75; stars gained: +52; forks gained: +2.
Language: C#
Topics: g14, mux, aura, g-helper, armoury, strix
Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.
GitHub repository with 1,429 stars and 98 forks.
Trending score: 1.04; stars gained: +1; forks gained: +0.
Language: C++
Topics: amd, deepseek, llama, llm, npu
AMD Strix Halo local LLM guide: direct 100.0 t/s 30B Qwen MoE on Ryzen AI MAX+ 395 / Radeon 8060S. Setup, benchmarks, raw evidence.
GitHub repository with 91 stars and 4 forks.
Trending score: 0.98; stars gained: +7; forks gained: +0.
Language: Python
Topics: amd, benchmark, gfx1151, inference, llama-cpp, llm
Community-driven documentation for the AMD BC-250 APU (Cyan Skillfish)
GitHub repository with 106 stars and 21 forks.
Trending score: 0.87; stars gained: +7; forks gained: +0.
Language: HTML
Topics: amd, bc250, community, documentation, gaming, hardware
The most powerful tool now. You can install OptiScaler and DLSS Enabler, modify upscalers, manage everything, and make your games smaller in size, all in one place.
GitHub repository with 113 stars and 1 forks.
Trending score: 0.80; stars gained: +6; forks gained: +0.
Topics: amd, compration, dlss, dlssenabler, fsr, game