web development, streamlined

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

[CVPR 2025] Learning Flow Fields in Attention for Controllable Person Image Generation

Multi-format archive and compression library

Archive library for browsers

😎 Curated list of awesome things regarding the WebAssembly (wasm) ecosystem.

Ola: Pushing the Frontiers of Omni-Modal Language Model

The TypeScript AI agent framework. ⚡ Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama.

🤖 Headless UI for Virtualizing Large Element Lists in JS/TS, React, Solid, Vue and Svelte

Swift Package to implement a transformers-like API in Swift

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

Streaming highlighting with Shiki. Useful for highlighting text streams like LLM outputs.

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

This is the official implementation of "Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams"

ComfyUI wrapper of catvton-flux

InspireMusic: A Unified Framework for Music, Song, Audio Generation.

Video Generation Foundation Models: https://saiyan-world.github.io/goku/

Cross-platform, customizable ML solutions for live and streaming media.

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

Embeddable Postgres with real-time, reactive bindings.

WebAssembly SQLite with support for browser storage extensions

Very fast Markdown parser and HTML generator implemented in WebAssembly, based on md4c

A Training-free Iterative Framework for Long Story Visualization

The modern, lightweight, performant, accessible and extensible drag & drop toolkit for React.

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。