Starred repositories
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
LTX Director and a variety of other custom ComfyUI nodes and workflows
Local-first browser AI video editor with WebGPU and agent skills helps to create any videos
[EMNLP2024 Demo], [ICASSP 2025], [ICASSP 2026] A user-friendly library for reproducible video moment retrieval and highlight detection. It also supports audio moment retrieval.
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
OmniShotCut is a sensitive and more informative SoTA on Shot Boundary Detection task.
🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine
MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.
Autonomous game development for Godot, Bevy, and Babylon.js with Claude Code and Codex
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
macOS app to set battery charge limit for Intel MacBooks
A local Chrome/Edge extension for recording website sessions, network activity, storage, screenshots, and user behavior into an exportable analysis package.
🦊 内置 AI 逆向 Agent 的 Firefox — 通用 JS/JSVMP/WASM/签名逆向工作站，SpiderMonkey 引擎层非侵入 trace，把加密参数从黑盒还原成不依赖浏览器的纯算法
免费无广告的追剧资源指南，人工精选资源、每天检测资源有效性。收录在线影视、影视APP、网盘搜索、磁力BT、字幕、TVBox / 影视仓空壳软件/配置地址、IPTV直播源、会员拼团、影视相关开源项目。开源，社区共同维护。
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…
The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero c…
Browser Harness | Self-healing harness that enables LLMs to complete any task.
Browser-native Office / PDF / CAD / archive viewer for internal web apps, with Vue, React, Svelte, jQuery, Web Components, and no server-side conversion.
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
[ECCV 2024] Official implementation of the paper "X-Pose: Detecting Any Keypoints"
Miso TTS is an 8 billion, highly emotive text-to-speech model
AI-Powered Watermark Remover using Florence-2 and LaMA: Remove watermarks from images and videos, including AI-generated content from Sora, Runway, and others. Features a modern PyWebview GUI.
AirLLM 70B inference with single 4GB GPU