LAYRA is a ready-to-use visual RAG system with a complete web UI built with Next.js and FastAPI, preserving document layout, tables, paragraphs, and graphical elements without any structural fragme…

OpenOmni: Official implementation of Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

minimal-cost for training 0.5B R1-Zero

Fully open reproduction of DeepSeek-R1

Ola: Pushing the Frontiers of Omni-Modal Language Model

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

Large Reasoning Models

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

LLM2CLIP makes SOTA pretrained CLIP model more SOTA ever.

✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model（端到端大模型）

GLM-4-Voice | 端到端中英语音对话模型

"LightRAG: Simple and Fast Retrieval-Augmented Generation"（GraphRAG的轻量级解决方案）

Framework for building, orchestrating and deploying multi-agent systems. Managed by OpenAI Solutions team. Experimental framework.（OpenAI多智能体框架）

SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

An open-source RAG-based tool for chatting with your documents.

Free and Open, Distributed, RESTful Search Engine

Solve puzzles. Learn CUDA.（CUDA编程）

A modular graph-based Retrieval-Augmented Generation (RAG) system

AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents

🚀 基于 LLM 大语言模型的知识库问答系统。开箱即用、模型中立、灵活编排，支持快速嵌入到第三方业务系统。

Lightning-fast serving engine for AI models. Flexible. Easy. Enterprise-scale.

A lightweight framework for building LLM-based agents（轻量级agent框架）

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Netease Youdao's open-source embedding and reranker models for RAG products.(网易开源的支持中英双语嵌入模型)

每个人都能用的数字人

Open Source framework for voice and multimodal conversational AI