Starred repositories
Collection of publicly available IPTV channels from all over the world
Unofficial cross-platform desktop client for the Hugging Face Hub
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
👩🏿💻👨🏾💻👩🏼💻👨🏽💻👩🏻💻中国独立开发者项目列表 -- 分享大家都在做什么
🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code…
A browser-based video editor powered by ffmpeg.wasm. No uploads, no servers -- all processing happens locally in your browser using WebAssembly.
MiMo Code: Where Models and Agents Co-Evolve
My personal Obsidian vault template. A bottom-up approach to note-taking and organizing things I am interested in.
Free Chat UIKit for React — 1,000 MAU/month free forever with push notifications & no concurrency limits. Build in-app chat UI in minutes with pre-built React components: conversation list, large c…
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
Download videos from almost any website. Lightweight, self-hosted media downloader with a clean web UI.
OpenReel Video - Professional browser-based video editor. Open source CapCut alternative. 100% browser-based, no installation, no cloud uploads, no watermarks.
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
Write HTML. Render video. Built for agents.
GEO experiment data reports and a curated GEO/AEO/AI search paper library.
Distribute and run LLMs with a single file.
Unrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 500+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT lice…
Create polished demo videos without editing skills. Mac/Windows/Linux
Abliterated Gemma 4 31B for Ollama and MLX — one-command setup with correct chat template fix
ncnn is a high-performance neural network inference framework optimized for the mobile platform
ncnn implementation of Z-Image image generater
cross-platform (Qt), open-source (GPLv3) video editor
👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
从 @anthropic-ai/claude-code npm 包的 cli.js.map 中还原出的完整 TypeScript 源码，可一键本地编译运行。