AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Stable Diffusion web UI

Interact with your documents using the power of GPT, 100% privately, no data leaks

real time face swap and one-click video deepfake with only a single image

the only cheat sheet you need

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Let us control diffusion models!

one-click face swap

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Open-Sora: Democratizing Efficient Video Production for All

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

DSPy: The framework for programming—not prompting—language models

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

Turns Data and AI algorithms into production-ready web applications in no time.

WebUI extension for ControlNet

Python scraper based on AI

State-of-the-Art Text Embeddings

Privacy-respecting metasearch engine

An open source implementation of CLIP.

Structured Text Generation

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

Running large language models on a single GPU for throughput-oriented scenarios.

ImageBind One Embedding Space to Bind Them All

Fast and Accurate ML in 3 Lines of Code

fast-stable-diffusion + DreamBooth

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Large Action Model framework to develop AI Web Agents

🌊 Online machine learning in Python