Let Codex and Claude Code ping each other

The Little Book of Reinforcement Learning

OpenBot leverages smartphones as brains for low-cost robots. We have designed a small electric vehicle that costs about $50 and serves as a robot body. Our software stack for Android smartphones su…

14MB foundation model for tiny devices; phones, wearables, smart home, and robots.

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

A set of training recipes for AI Quantum Error Correction Decoders

Lossless DFlash speculative decoding for MLX on Apple Silicon

🕹️ Is this the smallest language model in the world? I just managed to squeeze real artificial intelligence into 30 kilobytes, running on a 1979 Atari 800. A fully generative, deterministic languag…

Hysteria is a powerful, lightning fast and censorship resistant proxy.

企业微信开放平台命令行工具 — 让人类和 AI Agent 都能在终端中操作企业微信

Site-backed dataset, reconciled package files, and interactive docs for OpenAI vs Anthropic compute estimates.

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

Multi-LoRA inference server for Apple Silicon -- one base model, many adapters, zero reload

A curated list of awesome projects, tools, and resources for Apple MLX — the ML framework for Apple Silicon

Git-Native Coding Agent for Mac

Run frontier AI locally.

Memory Sparse Attention - A scalable, end-to-end trainable latent-memory framework for 100M-token contexts.

State-of-the-art TTS model under 25MB 😻

Running a big model on a small laptop

Your personal intelligence agent. Watches the world from multiple data sources and pings you when something changes.

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.

LLM Architecture Gallery source data

Desktop and web interface for OpenCode AI agent

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork

Personal AI, On Personal Devices

Minimalist ML framework for Rust