Starred repositories
PrismML-Eng / llama.cpp
Forked from ggml-org/llama.cppLLM inference in C/C++
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
Master programming by recreating your favorite technologies from scratch.
PC Software for BambuLab and other 3D printers
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
An app that brings language models directly to your phone.
Policy-driven, layered isolation and containment
Home-enthusiast's guide to fine-tuning 27B+ LLMs on AMD Strix Halo (gfx1151, Ryzen AI MAX+ 395) — the patches and tuning to make Linux mainline + ROCm 7.13 nightly + PyTorch 2.11 + bitsandbytes + f…
Evidence-backed AMD Strix Halo local-AI setup and benchmarks: Qwen3.8, Ollama, llama.cpp, Vulkan/ROCm, large GGUFs, and cross-OEM results.
Run Qwen 3.6-27B AWQ-INT4 models with DFlash speculative decoding on AMD Strix Halo hardware using vLLM for high-throughput inference.
vLLM Qwen 3.6-27B (AWQ-INT4) + DFlash speculative decoding on AMD Strix Halo (gfx1151 iGPU, 128 GB UMA, ROCm 7.13). 24.8 t/s single-stream, vision, tool calling, 256K context, OpenAI-compatible, Do…
Project NOMAD is an offline-first knowledge and education server. Wikipedia, thousands of books, courses, maps, and optional local AI, all running on hardware you own with no internet required.
The open-source alternative to Claude Cowork (powered by opencode)
A powerful AI coding agent. Built for the terminal.
The easiest, most secure way to use WireGuard and 2FA.
Replay a GitHub Copilot CLI session from its events.jsonl at a controllable speed. Built for stage demos — no network, no Copilot service calls.
Squad agents on Azure Container App Jobs — event-driven, serverless agent orchestration
An open-source AI coding agent that lives in your terminal.
AI agents running research on single-GPU nanochat training automatically
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
iOS client for coding agents via ACP or Codex app-server
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.
The best-benchmarked open-source AI memory system. And it's free.
Run GitHub Copilot CLI with local models - airplane mode 🛫
Squad Places - A social network for Squads [because that's SUCH a good idea?]
The agent that grows with you