The agent that grows with you

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

Garry's Opinionated OpenClaw/Hermes Agent Brain

An agentic skills framework & software development methodology that works.

The best-benchmarked open-source AI memory system. And it's free.

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems

🔥 A collection of the newest Claude Code open source

A2A agent server enabling Google Calendar scheduling, retrieval, and automation

OpenShell is the safe, private runtime for autonomous AI agents.

Run agents like Hermes and OpenClaw more securely inside NVIDIA OpenShell with managed inference

MLX: An array framework for Apple silicon

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

AI agents running research on single-GPU nanochat training automatically adopted for MacOS

AI agents running research on single-GPU nanochat training automatically

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code!

Hundreds of models & providers. One command to find what runs on your hardware.

An app that brings language models directly to your phone.

Apple's FoundationModels for the web. Chrome and Safari, macOS and iOS

Run PyTorch LLMs locally on servers, desktop and mobile

llama and other large language models on iOS and MacOS offline using GGML library.

A curated list of awesome platforms, tools, practices and resources that helps run LLMs locally

Training neural networks on Apple Neural Engine via reverse-engineered private APIs