AnythingLLM
All-in-one desktop and Docker app for private document chat and agents.
- Stars
- 67.1K
- Forks
- 7.5K
- Open issues
- 330
- Last commit
- 2026-10-15
Live from the GitHub API · updated 2026-10-15
What is AnythingLLM?
AnythingLLM turns documents, websites and code into a private knowledge base you can chat with using local or cloud models. It includes built-in vector storage, agents, multi-user workspaces and an embeddable chat widget.
Key features
- Workspaces with document RAG
- Built-in LLM, embedder and vector DB options
- No-code agents and tools
- Embeddable chat widget
System requirements
- Platforms
- Windows · macOS · Linux · Docker
- RAM
- 2 GB+ for the app; more for local models
How to install AnythingLLM
Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.
Desktop app
- 1Download from anythingllm.com and run the installer.
Docker
- 1Run the server (http://localhost:3001).
docker pull mintplexlabs/anythingllm docker run -d -p 3001:3001 --cap-add SYS_ADMIN -v $HOME/anythingllm:/app/server/storage -e STORAGE_DIR="/app/server/storage" mintplexlabs/anythingllm
Strengths
- Easiest private RAG setup
- MIT license
Limitations
- RAG quality depends on chunking settings
AnythingLLM alternatives compared
| Software | Stars | License | Platforms | VRAM |
|---|---|---|---|---|
| AnythingLLM All-in-one desktop and Docker app for private document chat and agents. | 67.1K | MIT | — | |
| Open WebUI Self-hosted ChatGPT-style interface for Ollama and OpenAI-compatible APIs. | 155.7K | Open WebUI License (BSD-3-Clause based) | — | |
| RAGFlow RAG engine built on deep document understanding. | 92.3K | Apache-2.0 | — | |
| Dify Visual platform for building LLM apps, RAG pipelines and agents. | 158.5K | Dify Open Source License (Apache-2.0 based) | — | |
| GPT4All Private, on-device chat with local document Q&A. | 77.4K | MIT | — | |
| LibreChat Open-source ChatGPT clone supporting every major AI provider. | 45.7K | MIT | — |
FAQ
Is AnythingLLM free?
Yes — AnythingLLM is open-source software released under the MIT license. Check the license (and any model weight licenses) before commercial use.
Does AnythingLLM run on Windows, Mac and Linux?
AnythingLLM supports: Windows, macOS, Linux, Docker.
What hardware do I need for AnythingLLM?
RAM: 2 GB+ for the app; more for local models
How do I install AnythingLLM?
1. Download from anythingllm.com and run the installer.
What are the best AnythingLLM alternatives?
Popular alternatives include Open WebUI, RAGFlow, Dify, GPT4All. See the comparison table on this page.