Mintplex Labs

license

MIT(OSI)

source

public

core features withheld

no

Fully OSI (MIT), full source public; a hosted instance is offered but the self-hosted Desktop/Docker app is the complete product. Multi-user permissioning and the embeddable chat widget are marked Docker-version-only, but both ship in the MIT repository, so nothing is withheld from the published source.

• https://anythingllm.com/ recorded 2026-09-29

  The homepage states "MIT Licensed. Open Source." and "AnythingLLM is fully open-source and licensed for organizational use. Self-host a multi-user deployment on your own servers, or just use the desktop app."

• https://github.com/Mintplex-Labs/anything-llm recorded 2026-08-13

  MIT license; all-in-one local-first RAG/agent app, v1.13.0

Adoption is measured by Docker Hub pulls of the official image, the only distribution channel with a public count. The desktop build ships separately from Docker and is not included in that count, which is why confidence here is medium rather than high.

• https://hub.docker.com/r/mintplexlabs/anythingllm recorded 2026-08-13

  1M+ total Docker pulls; ~45,859 pulls this week

AnythingLLM combines broad provider and vector-database support with retrieval-augmented generation, multi-user permissioning, and no-code agents that include web browsing, putting it on par with LibreChat and Open WebUI. It also adds scheduled cron tasks, managed memories and automatic skill selection, though the broadest open-source leaders still ship an even wider feature set.

• https://anythingllm.com/ recorded 2026-10-07

  Homepage: a "Meeting Assistant" that "Automatically transcribes and summarizes any meeting entirely on your computer", and "Self-host a multi-user deployment on your own servers, or just use the desktop app."

• https://github.com/Mintplex-Labs/anything-llm recorded 2026-08-31

  40+ LLM providers, RAG, multi-user permissioning, no-code agents with web browsing

• https://raw.githubusercontent.com/Mintplex-Labs/anything-llm/master/README.md recorded 2026-10-07

  README feature list: "Dynamic Model Routing", "Automatic & User Managed Memories", "No-code AI Agent builder", "MCP-compatibility", "Multi-modal support (both closed and open-source LLMs!)", "Multi-user instance support and permissioning" and "Agents inside your workspace (browse the web, etc)", with a supported-provider section of close to forty LLM providers and nine vector databases.