Stars
Intelligent automation and multi-agent orchestration for Claude Code
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…
Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.
A modern cookiecutter template for Python projects that use uv for dependency management
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data
Get your documents ready for gen AI
An open-source RAG-based tool for chatting with your documents.
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
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
GenAI Agent Framework, the Pydantic way
Model Context Protocol Servers
Extract full next-token probabilities via language model APIs
⚡ TabPFN: Foundation Model for Tabular Data ⚡
A little word cloud generator in Python
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
CLI platform to experiment with codegen. Precursor to: https://lovable.dev
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Python tool for converting files and office documents to Markdown.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
AdalFlow: The library to build & auto-optimize LLM applications.
Entropy Based Sampling and Parallel CoT Decoding
Easily train a good VC model with voice data <= 10 mins!
A generative speech model for daily dialogue.
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.