Local Qwen3 LLM inference. One easy-to-understand file of C source with no dependencies.

HAL (HTTP API Layer) is a Model Context Protocol (MCP) server that provides HTTP API capabilities to Large Language Models.

An open-source, high-resolution scrolling Knob, powered by QMK.

An open-source AI agent that brings the power of Gemini directly into your terminal.

Take your LLM to the optometrist.

A framework for managing and maintaining multi-language pre-commit hooks.

Some out-of-the-box hooks for pre-commit

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

Simplified Gemini for Claude Code.

From data to vector database effortlessly

ChatSnapshot is a lightweight, framework-agnostic library designed to persist, restore, and transport full agentic chat sessions

Server for alignment and comms

MCP examples

A TTS model capable of generating ultra-realistic dialogue in one pass.

An open protocol enabling communication and interoperability between opaque agentic applications.

A benchmark of tasks against the AG2 ethical principles

Implementing OCR with a local visual model run by ollama.

Multi-agent system for science, powered by ag2

a simple example demonstrating MCP + ag2 (autogen) integration

Optimized Ollama LLM server configuration for Mac Studio and other Apple Silicon Macs. Headless setup with automatic startup, resource optimization, and remote management via SSH.

AI assisted web scraping and data extraction

Move and resize windows on macOS with keyboard shortcuts and snap areas

Programming language that targets the Nintendo Entertainment System