🙌 OpenHands: Code Less, Make More

The official Meta Llama 3 GitHub site

Open-Sora: Democratizing Efficient Video Production for All

Composio equips your AI agents & LLMs with 100+ high-quality integrations via function calling

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

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

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

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

Python scraper based on AI

SGLang is a fast serving framework for large language models and vision language models.

Examples and guides for using the Gemini API

Automate browser-based workflows with LLMs and Computer Vision

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

⚡️Wren AI is your GenBI Agent, that you can query any database with natural language → get accurate SQL(Text-to-SQL), charts(Text-to-Charts) & AI-generated insights in seconds.

Building a quick conversation-based search demo with Lepton AI.

Start building LLM-empowered multi-agent applications in an easier way.

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

A UI-Focused Agent for Windows OS Interaction.

Large Action Model framework to develop AI Web Agents

No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents

Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.

The open source platform for AI-native application development.

The most advanced AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.

🚀 KIMI AI 长文本大模型逆向API【特长：长文本解读整理】，支持高速流式输出、智能体对话、联网搜索、探索版、K1思考模型、长文档解读、图像解析、多轮对话，零配置部署，多路token支持，自动清理会话痕迹，仅供测试，如需商用请前往官方开放平台。

The world's first open-source "Vibe Workflow" platform for complex tasks.

Knowledge Agents and Management in the Cloud

AIOS: AI Agent Operating System

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

🤖 𝗟𝗲𝗮𝗿𝗻 for 𝗳𝗿𝗲𝗲 how to 𝗯𝘂𝗶𝗹𝗱 an end-to-end 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗟𝗟𝗠 & 𝗥𝗔𝗚 𝘀𝘆𝘀𝘁𝗲𝗺 using 𝗟𝗟𝗠𝗢𝗽𝘀 best practices: ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 12 𝘩𝘢𝘯𝘥𝘴-𝘰𝘯 𝘭𝘦𝘴𝘴𝘰𝘯𝘴

Run PyTorch LLMs locally on servers, desktop and mobile

Devon: An open-source pair programmer

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

DeepSeek-VL: Towards Real-World Vision-Language Understanding

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.

仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

Build AI assistants that interact with your systems

LLM Zoomcamp - a free online course about real-life applications of LLMs. In 10 weeks you will learn how to build an AI system that answers questions about your knowledge base.

Neo4j graph construction from unstructured data using LLMs

Open source Tines / Splunk SOAR alternative. All-in-one automation platform (workflows, tables, cases) for security and IT teams.

基于大模型的智能对话客服工具，支持微信、拼多多、千牛、哔哩哔哩、抖音企业号、抖音、抖店、微博聊天、小红书专业号运营、小红书、知乎等平台接入，可选择 GPT3.5/GPT4.0/ 懒人百宝箱 （后续会支持更多平台），能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业 AI 应用。

One for All Modalities Evaluation Toolkit - including text, image, video, audio tasks.

Open weights LLM from Google DeepMind.

CSGHub is an open-source large model platform just like on-premise version of Hugging Face. You can easily manage models and datasets, deploy model applications and setup model finetune or inference jobs with user interface. CSGHub also provides Python SDK with full compatibility of hf sdk. Join us together to build a safer and more open platform⭐️

⚡ Lingo.dev - open-source, AI-powered i18n toolkit for instant localization with LLMs. Bring your own LLM or use Lingo.dev engine. Join discord: https://lingo.dev/go/discord

Gemini ➜ OpenAI API proxy. Serverless!

pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai

FinRobot: An Open-Source AI Agent Platform for Financial Analysis using LLMs 🚀 🚀 🚀

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

Use API to call the music generation AI of suno.ai, and easily integrate it into agents like GPTs.

Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, VectorDBs, Agent Frameworks and GPUs.

A new customer-facing LLM-agent framework to increase accuracy and reliability

心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

Training LLMs with QLoRA + FSDP

The easiest way to get started with LlamaIndex

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

chatGPT、prompt、LLM

基于.Net8+AntBlazor+SemanticKernel 和KernelMemory 打造的AI知识库/智能体，支持本地离线AI大模型。可以不联网离线运行。支持aspire观测应用数据

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

RAG Search API

LLM powered fuzzing via OSS-Fuzz.

Framework to build resilient language agents as graphs.

Sora AI Video Generator by Sora.FM

AI-Powered Penetration Testing Assistant

A @ClickHouse fork that supports high-performance vector search and full-text search.

A unified interface for working with LLMs in Laravel

Examples and guides for using the GLM APIs

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

GenAI Cookbook

Scalable data pre processing and curation toolkit for LLMs

Build your own serverless AI Chat with Retrieval-Augmented-Generation using LangChain.js, TypeScript and Azure

🐝 GPTSwarm: LLM agents as (Optimizable) Graphs

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

Langtrace 🔍 is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorDBs and more.. Integrate using Typescript, Python. 🚀💻📊

🚀 智谱清言ChatGLM-4-Plus大模型逆向API【特长：超强智能体】，支持高速流式输出、支持智能体对话、支持多轮对话、支持沉思模型、支持Zero思考推理模型、支持视频生成、支持AI绘图、支持联网搜索、支持长文档解读、支持代码调用、支持图像解析，零配置部署，多路token支持，自动清理会话痕迹，仅供测试，如需商用请前往官方开放平台。

A PyTorch Native LLM Training Framework

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"

csghub-server is the backend server for CSGHub which helps user to manage datasets, modes, and also run Model Inference, Finetune and Application Spaces.

Low-bit LLM inference on CPU with lookup table

structured extraction for llms

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

MobiLlama : Small Language Model tailored for edge devices

Generative Representational Instruction Tuning

Official code for Goldfish model for long video understanding and MiniGPT4-video for short video understanding

Train Models Contrastively in Pytorch

A demo application using fal.realtime and the lightning fast SDXL API provided by fal

The most advanced Web UI for AI chat

A personal wearable AI that runs locally

Advanced Quantization Algorithm for LLMs and VLMs, with support for CPU, Intel GPU, CUDA and HPU. Seamlessly integrated with Torchao, Transformers, and vLLM.

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

[ACL 2024] Progressive LLaMA with Block Expansion.

State-of-the-art bilingual open-sourced Math reasoning LLMs.

The React library for LLMs

Efficient AI Inference & Serving

Video Search and Streaming Agent 🕵️‍♂️