Stars
Self host your media and share with unique links
Your self hosted YouTube media server
A ~9M parameter LLM that talks like a small fish.
Specification and documentation for Agent Skills
A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
My personal directory of skills, straight from my .claude directory.
Open Claude Is Open-source coding-agent CLI for OpenAI, Gemini, DeepSeek, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.
TypeScript multi-agent framework — one runTeam() call from goal to result. Auto task decomposition, parallel execution. 3 dependencies, deploys anywhere Node.js runs.
Textream is a free macOS teleprompter app for streamers, interviewers, and presenters. It highlights your script in real-time as you speak, displayed in a beautiful Dynamic Island overlay. With ext…
[IJCAI'24] Beyond Alignment: Blind Video Face Restoration via Parsing-Guided Temporal-Coherent Transformer
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
Running Docling as an API service
Mac app that shows all open files, directories, sockets, pipes and devices in use by all running processes. Nice GUI for lsof.
Like Vercel, but open source and for all languages.
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
Wan: Open and Advanced Large-Scale Video Generative Models
Multilingual Document Layout Parsing in a Single Vision-Language Model
Refine high-quality datasets and visual AI models
Machine Learning Engineering Open Book
A python tool that uses GPT-4, FFmpeg, and OpenCV to automatically analyze videos, extract the most interesting sections, and crop them for an improved viewing experience.