AnythingLLM
An all-in-one AI application for chatting with your documents and running AI agents locally, with multi-user support and desktop and Docker versions.
- GitHub stars
- 67k
- Last commit
- yesterday
- Latest release
- v1.17.0
- Licence
- MIT
- Self-hosted
- Yes
- Hosted version
- Available

AnythingLLM is an all-in-one AI application for chatting with your own documents and automating work with AI agents. It runs locally by default, lets you connect local or cloud language models, and is written in JavaScript under the MIT license. The README describes it as a way to build a private, fully featured assistant in the style of ChatGPT.
Vector databases, document processing pipelines, multi-user support and agents all come included. Newer features listed include dynamic model routing based on rules you define, automatic and user-managed memories, scheduled tasks with agent capabilities, skill selection, a no-code agent builder, MCP compatibility and multi-modal support for both closed and open-source models.
It is available as a desktop app for Mac, Windows and Linux, as a Docker version that adds multi-user access control, and as a hosted instance, and there is an open-source Android app. Administrators can control access and experience per user. It suits individuals and teams who want a private document-chat and agent workspace without much setup.
Key features
- Chat with your documents using RAG
- Built-in AI agents and no-code agent builder
- Multi-user access control in Docker version
- Connects to local or cloud LLMs
- Vector database and document pipeline support
- MCP compatibility and scheduled tasks
- Desktop apps for Mac, Windows and Linux
Pricing: Self-hosting with Docker is free. Hosted Cloud costs $50 per month (Basic) or $99 per month (Pro); Enterprise with on-premise deployment is quoted on request.
