Three.cad is a 3D modelling software built using Three.js, React, and Web Assembly. It features parametric sketching and constructive solid geometry (CSG) capabilities.

Scan for React performance issues and eliminate slow renders in your app

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Prompt, run, edit, and deploy full-stack web applications using any LLM you want!

FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations

Official repository for LTX-Video

Open-source developer platform to power your entire infra and turn scripts into webhooks, workflows and UIs. Fastest workflow engine (13x vs Airflow). Open-source alternative to Retool and Temporal.

Examples with SwiftUI that showcase various interactions, animations and more

A modern animation library for React and JavaScript

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

Unlock your displays on your Mac! Flexible HiDPI scaling, XDR/HDR extra brightness, virtual screens, DDC control, extra dimming, PIP/streaming, EDID override and lots more!

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

first base model for full-duplex conversational audio

Get your documents ready for gen AI

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

A simple screen parsing tool towards pure vision based GUI agent

A collection of projects designed to help developers quickly get started with building deployable applications using the Anthropic API

AI agent workflow for generating profiles of clients and running research tasks for them. There is an agent for each part of the process: profile generation, web search, and report writing.

Detect and extract tables to markdown and csv

Local realtime voice AI

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

An engine to run your pipelines in containers

Code of Pyramidal Flow Matching for Efficient Video Generative Modeling

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

A Foundation for Scalable Cross-Platform Apps

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Label Studio is a multi-type data labeling and annotation tool with standardized output format

[MM 2024] [Need only a 3090] MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors

https://textbehindimage.rexanwong.xyz - create text behind image designs easily

Build real-time multimodal AI applications 🤖🎙️📹