[CVPR2025] Official repository for “MagicArticulate: Make Your 3D Models Articulation-Ready”

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

An experiment in meeting transcription and diarization with just an LLM. Maybe I went a little overboard though

A lightweight CLI and local API server to create, run and manage macOS and Linux virtual machines (VMs) natively on Apple Silicon.

Screen-space raymarched godrays for three.js using the pmndrs postprocessing library

Custom elements (web components) for making audio and video player controls that look great in your website or app.

An AI web browsing framework focused on simplicity and extensibility.

🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser instance that lets you automate the web without worrying about infrastructure.

Awesome MCP Servers - A curated list of Model Context Protocol servers

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

[CVPR 2025] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

Window management made elegant.

A component toolkit for creating live-running code editing experiences, using the power of CodeSandbox.

[ICLR 2025] InstantSwap: This repo is the official implementation of "InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences"

[CVPR'25] Official Implementations for Paper - MagicQuill: An Intelligent Interactive Image Editing System

ZIM: Zero-Shot Image Matting for Anything

An open source framework to add the effects of traveling at relativistic speeds to visualizations or games

Modern open-source time-tracking app

TypeScript-centric app development platform: notebook and AI app builder

Entropy Based Sampling and Parallel CoT Decoding

A from-scratch experimental AOT JS engine, written in JS

A python wrapper for the public & private Spotify API

Deepgram Conversational AI demo

We write your reusable computer vision tools. 💜

Official repo of 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗠𝗼𝗱𝗲𝗹𝘀: 𝗪𝗵𝗮𝘁 𝗗𝗼 𝗧𝗵𝗲𝘆 𝗞𝗻𝗼𝘄? 𝗗𝗼 𝗧𝗵𝗲𝘆 𝗞𝗻𝗼𝘄 𝗧𝗵𝗶𝗻𝗴𝘀? 𝗟𝗲𝘁'𝘀 𝗙𝗶𝗻𝗱 𝗢𝘂𝘁! (Previously titled 𝘐𝘯𝘵𝘳𝘪𝘯𝘴𝘪𝘤 𝘓𝘰𝘙𝘈: 𝘈 𝘎𝘦𝘯𝘦𝘳𝘢𝘭𝘪𝘴𝘵 𝘈𝘱𝘱𝘳𝘰𝘢𝘤𝘩 𝘧𝘰𝘳 𝘋𝘪𝘴𝘤𝘰𝘷𝘦𝘳𝘪𝘯𝘨 𝘒𝘯𝘰𝘸𝘭𝘦𝘥𝘨𝘦 𝘪𝘯 𝘎𝘦𝘯𝘦𝘳𝘢𝘵𝘪𝘷𝘦 𝘔𝘰𝘥𝘦𝘭𝘴))

🌟 Open-source, visual programming for developers. Includes a VS Code extension, integrates with existing TypeScript code, browser and Node.js.

Lightweight WASM Postgres with real-time, reactive bindings.

A VM module for Node.js that utilizes the secure environment provided by Deno

Browse the web with GPT-4V and Vimium