Stars
[AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
Jitsi Meet - Secure, Simple and Scalable Video Conferences that you use as a standalone app or embed in your web application.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
Official Repository of "OmniTry: Virtual Try-On Anything without Masks"
Build AI applications that can see, hear, and speak using your screens, microphones, and cameras as inputs.
Embedded graphics library to create beautiful UIs for any MCU, MPU and display type.
A trusty face analysis research platform developed by Tencent Youtu Lab
Efficient face emotion recognition in photos and videos
[ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning
Open Source Machine Learning Research Platform designed for frontier AI/ML workflows. Local, on-prem, or in the cloud. Open source.
🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines
An extremely fast Python package and project manager, written in Rust.
UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
The open source developer platform to build AI agents and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integrated platform.
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous …
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
A simple screen parsing tool towards pure vision based GUI agent
Visualizing query-key interactions in language + vision transformers (VIS 2023)
Minimal reproduction of DeepSeek R1-Zero
DeepSeek LLM: Let there be answers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.