AnythingLLM

An all-in-one AI app for chatting with your documents and running agents, with a built-in vector database, multi-user support and desktop apps.

67.8k stars, 7.6k forks JavaScript On GitHub since June 2023

Visit website View on GitHub How to run it

What is AnythingLLM?

AnythingLLM bundles what a private ChatGPT needs: a connection to local or cloud models, document ingestion, a vector database, agents and multi-user access. You can run it as a desktop app on Mac, Windows or Linux, or as a Docker service for a team, and it works with Ollama, LM Studio and many hosted providers. Documents are organized into workspaces so each chat draws on its own sources. The interface is translated into 28 languages.

Good fit if

  • You want document chat that works out of the box, without wiring a vector database yourself.
  • You need the same tool on a laptop and as a shared server.
  • You want to control which users see which workspaces.

Look elsewhere if

  • You need advanced parsing of complex PDFs and scans: RAGFlow.
  • You want a general chat interface for many models without the document focus: Open WebUI.

Before you adopt it

AnythingLLM is MIT-licensed, developed by Mintplex Labs, and the paid hosted instance is optional. A Helm chart is included for Kubernetes deployments.

Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction

AnythingLLM health: is it still maintained?

94 of 100, actively developed

  • Activity
    356 commits in the last 90 days, the latest on 30 October 2026.
    30 / 30
  • Contributors
    33 people wrote the latest 100 commits; the most active wrote 24% of them.
    20 / 20
  • Releases
    15 releases in the last 12 months; the latest, v1.19.0, on 26 October 2026.
    19 / 20
  • Replies to issues
    Maintainers answered 100% of recent issues, with a median first reply after 5 hours.
    20 / 20
  • Security practices
    No OpenSSF Scorecard for this repository yet, so this part gets a neutral score.
    5 / 10

Read from GitHub on 1 November 2026. How the score works

AnythingLLM license: is it open source?

AnythingLLM uses MIT, an open-source license approved by the OSI.

  1. June 2023First published on GitHub.
  2. TodayMIT.

How to run AnythingLLM yourself

Docker
Dockerfile or compose file in the repository
Compose file
docker/docker-compose.yml: 1 service
Setup effort
1 of 5, judged from the compose file
Kubernetes
Helm chart in the repository
Desktop and mobile
Builds for Windows, macOS, Linux, including ARM in GitHub releases
Interface languages
28 languages

Install instructions: anythingllm.com or the README on GitHub.

Alternatives to AnythingLLM

  • RAGFlowRAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG… 93 health · Apache-2.0 · 93.3k stars
  • Hermes AgentThe agent that grows with you 76 health · MIT · 259k stars
  • MaxKBMaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。 82 health · GPL-3.0 · 23.1k stars
  • DocsGPTPrivate AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research,… 84 health · MIT · 18.4k stars
  • FastGPTFastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box… 82 health · FastGPT Open Source License · 30k stars

All 36 projects in AI chat & local LLMs

Questions about AnythingLLM

Is AnythingLLM open source?

Yes. AnythingLLM is published under MIT, an OSI-approved open-source license.

Is AnythingLLM still maintained?

Its health score is 94 of 100 (actively developed). It had 356 commits in the last 90 days, the latest on 30 October 2026, and its latest release came out on 26 October 2026.

How do I run AnythingLLM?

You can run it with Docker, on Kubernetes with the Helm chart in the repository, as an app for Windows, macOS, Linux, including ARM. The README on GitHub has the exact steps.

What are the alternatives to AnythingLLM?

Close alternatives in the AI chat & local LLMs category include RAGFlow, Hermes Agent, MaxKB.