AMD Strix Halo local LLM guide: setup for Ryzen AI MAX+ 395 / Radeon 8060S, Ollama, llama.cpp Vulkan/RADV, ROCm, raw evidence, direct 100 t/s 30B Qwen, 140 t/s CHADROCK MTP, 120B GGUF.

Local LLM Server Manager + LlaMA.cpp + Chat

Local only minimal coding harness

A vector index built on TurboQuant, written in Rust with Python bindings

Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.

Random AI notes for working with local models or playing around with random machine learning bits.

Profile-guided GPU kernel optimizer for AMD/RDNA3. Auto-tunes llama.cpp MMVQ kernels per model shape. 2x decode speedup on 7900 XTX.

AI agents running research on single-GPU nanochat training automatically

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Devin's attempt at creating an OpenSCAD MCP Server that takes a user prompt and generates a preview image and 3d file.

Natural voice conversations with Claude Code

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

An agentic workflow tool that provides context engineering support for opencode

Kandinsky 5.0: A family of diffusion models for Video & Image generation

Foundational Model for Speech Recognition Tasks

ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

Beads - A memory upgrade for your coding agent

Lightweight static analysis for many languages. Find bug variants with patterns that look like source code.

An open-source multi-provider AI assisted CLI development tool. Use whatever LLM you want to code in your terminal.

vllama is an open source hybrid server that combines Ollama's seamless model management with vLLM's lightning-fast GPU inference, delivering a drop-in OpenAI-compatible API for optimized performance.

PCB assembly software for Makers, including planning, pick-and-place and gerber viewing.

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai

Tool to display AMDGPU usage

LLM inference in C/C++

MicroStrain Communication Library

ROS driver for all of MicroStrain's current G and C series products. To learn more visit