Stars
毛选.skill — 让毛泽东的思维框架帮你分析问题、制定策略、看透本质。7个核心心智模型 · 10条决策启发式 · 完整表达DNA。不是复读语录，是用他的认知框架帮你看问题。
Orchestrate coding agents remotely from your phone, desktop and CLI
The world's most sophisticated street level image geolocation software
π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.
A dataset of 222 digital musical scores aligned with 1068 performances (more than 92 hours) of Western classical piano music.
MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API)
Edit Banana: A framework for converting statistical formats into editable.
《动手学大模型Dive into LLMs》系列编程实践教程
Smallest transformer that can add two 10-digit numbers
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX …
A self-evolving open source project. Every week, the community votes on PRs, and the winner gets merged.
bilibili 硬核会员 AI 自动答题脚本，直接调用 B 站 API，非 OCR 实现
Fully automatic censorship removal for language models
AI gets the context. Not your secrets. Open-source privacy proxy for LLMs.
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
Automated music downloader and manager integrating Slskd and Beets.
While we are waiting for the official translation from MangaGamer, why not translate the game with ChatGPT?
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
Multi-platform implementation of AliceSoft's System3.x game engine.
利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.
A modern web client for Jellyfin based on Vue
HomeTube is a friendly video downloader managing single video URL into organized content structure for automatic home media server experience.