A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Own your compute, own your intelligence. Time to build your Personal AI Data Center.

Open-source AI agentic harness for property management operations. By the industry, for the industry.

OpenHuman is an open source agent harness with local-first memory, agent orchestration, and workflows

Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, and structured output. Supports vLLM, SGLang, and llama.cpp.

microGPT benchmarks: a single M4 Max MacBook Pro P-core in C runs Karpathy's 4192-parameter transformer at ~71x the throughput of TALOS-V2's FPGA implementation.

Web dashboard for exo, the open-source distributed Apple Silicon inference framework

Run any agent on any model, models stored as OCI images

A repo of useful MLX skills.

Infer Ring is an iOS and macOS app that facilitates cross-device LLM inference using MLX

mactop - Apple Silicon Monitor Top

Archive: Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

⚙️ A macOS DMG package builder with a native GUI and CLI support

Pretraining and inference code for a large-scale depth-recurrent language model

Artificial Neural Engine Machine Learning Library

The CLI for GPUs

Vane is an AI-powered answering engine.

A systematic reasoning MCP server implementation for Claude Desktop with beam search and thought evaluation.

EXO Gym is an open-source Python toolkit that facilitates distributed AI research.

Private Web Search for Local LLMs

Inference Llama models in one file of pure C for Windows 98 running on 25-year-old hardware

AI that sees your screen, listens to your conversations and tells you what to do

Sidecar is the AI brains for the Aide editor and works alongside it, locally on your machine

The open-source AI-native IDE

The Modular Platform (includes MAX & Mojo)

Official inference framework for 1-bit LLMs

MLX: An array framework for Apple silicon

A high-throughput and memory-efficient inference and serving engine for LLMs

convert images, video to ascii!

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.