Stars
experimental linux kernel modules and userspace drivers for RDMA-over-usb4/thunderbolt on consumer hardware
DeepSeek-V4-Flash across two Strix Halo boxes over 100GbE RDMA: llama.cpp patches, launch config, and measured results. 273 t/s prefill / 21.5 t/s decode at 8k.
ggml speech-to-text inference for 16+ model families
Режим идиоматического русского мата для AI-агентов. Короче, душевнее, эффективнее. 18+
A tool to unlobotomize your NVIDIA card!
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
cut Claude Code token usage by rendering text context as images
Port of Nvidia LocateAnything-3B on ggml
A QR code generator in a TrueType font: https://qr.jim.sh/
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
A FUSE-based virtual file system driver for dynamic OpenCode model discovery and configuration mapping.
Interactive BC-250 CU/WGP live manager using UMR, with TUI controls, safety checks, and boot-table persistence.
Re-enable all 40 CUs on the AMD BC-250 (gfx1013 / Cyan Skillfish). Kernel patch + build script. 1.61x compute scaling verified.
Super Productivity is an advanced todo list app with integrated Timeboxing and time tracking capabilities. It also comes with integrations for Jira, GitLab, GitHub and Open Project.
Python tool for converting files and office documents to Markdown.
Community recipes for serving LLMs on RTX 3090/4090/5090 CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B c…
A harness optimized to smaller LLMs
Build your own 'AirTags' 🏷 today! Framework for tracking personal Bluetooth devices via Apple's massive Find My network.
The best-benchmarked open-source AI memory system. And it's free.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI
neovim frontend for opencode - a terminal-based AI coding agent
SpinalHDL implementation of the 3dfx Voodoo Graphics GPU