Flash-Sparse-Attention

🚀🚀 Efficient implementations of Native Sparse Attention

最近更新: 2天前

vipe

ViPE: Video Pose Engine for Geometric 3D Perception

最近更新: 2天前

InfiniteTalk

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

最近更新: 2天前

Claudable

Claudable is an open-source web builder that leverages local CLI agents, such as Claude Code and Cursor Agent, to build and deploy products effortl...

最近更新: 2天前

mobile-use

AI agents can now use real Android and iOS apps, just like a human.

最近更新: 2天前

VibeVoice

Frontier Open-Source Text-to-Speech

最近更新: 2天前

rendergit

Render any git repo into a single static HTML page for humans or LLMs

最近更新: 2天前

memU

MemU is an open-source memory framework for AI companions

最近更新: 2天前

syncora-sdk

最近更新: 2天前

deepagents_1

最近更新: 2天前

dinov3

Reference PyTorch implementation and models for DINOv3

最近更新: 2天前

WeKnora

LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.

最近更新: 2天前

deepagents

最近更新: 2天前

ScreenCoder

ScreenCoder — Turn any UI screenshot into clean, editable HTML/CSS with full control. Fast, accurate, and easy to customize.

最近更新: 2天前

claude-code-security-review

An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.

最近更新: 2天前

KittenTTS

State-of-the-art TTS model under 25MB 😻

最近更新: 2天前

dots.ocr

Multilingual Document Layout Parsing in a Single Vision-Language Model

最近更新: 2天前

harmony

Renderer for the harmony response format to be used with gpt-oss

最近更新: 2天前

eigent

Eigent is the World's First Multi-agent Workforce to Unlock Your Exceptional Productivity.

最近更新: 2天前

Qwen-Image

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

最近更新: 2天前

搜索帮助