Zum Inhalt springen
AI.info

AI Tools

AnythingLLM

AnythingLLM: Preise, Fähigkeiten, Updates und Alternativen, von den Seiten des Anbieters gelesen.

Die Website von AnythingLLM

Auf Englisch

Key facts

Price
Free plan · paid plans from $50/mo Read on anythingllm.com
Free plan
Yes · Self-host with Docker Read on anythingllm.com
Platforms
Web · macOS · Windows · Linux · Android · Browser extension · API Read on anythingllm.com
API
Yes Read on docs.anythingllm.com
Open source
Yes · MIT Read on github.com
Latest version
v1.20.0 Read on docs.anythingllm.com
Last update
26 Oct 2026 Read on github.com
Prices checked
26 Oct 2026 Read on anythingllm.com

AnythingLLM lets individuals and teams chat with documents using retrieval-augmented generation (RAG), run agents with tools, and connect local or cloud language models. It can run on a computer, on an Android phone, in a self-hosted Docker setup, or as a hosted team workspace.

The desktop app and Docker self-hosting are free. Hosted Cloud plans cost extra; the Basic plan requires you to bring an LLM API key, so model-provider charges may also apply. Features and privacy depend in part on the model and services you choose.

Category
Developer Tools
Read from the maker’s pages
2026-11-18

Company

Mintplex Labs

Features

  • Index documents and retrieve relevant passages for chats
  • Run agents that search the web, summarize documents, and save files
  • Connect local and cloud language models, embedding models, and vector databases
  • Route requests between models using configurable rules
  • Schedule recurring agent jobs
  • Manage workspaces through a developer API
  • Use a browser extension to add context and chat

Use cases

  • Chat with a collection of work or research documents
  • Run an agent to search the web and summarize its findings
  • Schedule recurring tasks that use workspace documents
  • Build a private team AI workspace with Docker
  • Connect a local model for on-device document chat

Pricing

Free plan · paid plans from $50/mo

Prices checked
2026-10-26

Self-host with Docker

free

  • Self-host with Docker

Basic

$50/mo

  • $50 /monthly
  • Private instance
  • Custom subdomain
  • RAG, agents, and work right out of the box
  • Just bring an LLM API Key

Pro

$99/mo

  • $99 /monthly
  • Private instance
  • RAG, agents, work right out of the box
  • Great for large teams
  • 72-hour support SLA

Enterprise

price on request

  • On-premise deployment
  • Custom SLA
  • Custom integrations
  • SSO, RBAC, and more

Capabilities

  • Choice of models — “Select your preferred model or let AnythingLLM auto-recommend the best one for your hardware specs and our experience.” source
  • Self-hosted — “Give your whole team a private, multi-user AI workspace — hosted by us or self-hosted on your infrastructure.” source
  • API — “the custom tool builder and developer API make it easy to fit AnythingLLM to your exact needs - no extra bloat.” source
  • Builds agents and workflows — “Fully customizable Swap models, configure permissions, set up custom agent workflows, and white-label the interface to match your brand.” source
  • Search over your data — “RAG, agents, and work right out of the box” source

Latest updates

  • AnythingLLM v1.19.0

    Docker adds a built-in local LLM experience via Lemonade, with GPU acceleration and support for amd64 and arm64 hosts.

  • AnythingLLM v1.18.0

    Fixed Kubernetes probes, file and image handling, provider history attachments, embed allowlists, agent tool parameters, and SDK retry handling.

  • AnythingLLM v1.17.0
  • AnythingLLM v1.16.0

    Added image generation via /img and file picker support for dragging folders and files into existing folders.

  • AnythingLLM v1.15.0

    Launched desktop Magic Features: dictation, text actions, and autocomplete; Pro removes their daily limits.

Where it works

Web · macOS · Windows · Linux · Android · Browser extension · API

Alternatives to AnythingLLM

  • Open WebUI

    Self-hosted AI interface for chatting with local or cloud models, searching documents, and connecting tools.

  • Weaviate

    Weaviate is an open-source vector database for storing and searching data in AI applications, with self-hosted and managed cloud options.

  • Dify

    Build, deploy, and monitor AI apps, agents, workflows, and knowledge pipelines using hosted or self-hosted Dify.

  • GPT4All

    GPT4All runs open-source language models locally and lets users chat with models and their documents on desktop computers.

  • Jan

    Jan is an open-source desktop app for running AI models locally or connecting to cloud providers, with tools for research, files and coding.

  • LangFlow

    Langflow lets developers build, test, and deploy AI workflows, agents, and MCP servers with a visual editor and Python components.

Questions about AnythingLLM

Is AnythingLLM free?

Yes. AnythingLLM has a free plan, called Self-host with Docker. Paid plans start at $50/mo. Prices checked on 26 Oct 2026.

How much does AnythingLLM cost?

The plans on the maker’s pricing page: Self-host with Docker (free), Basic ($50/mo), Pro ($99/mo) and Enterprise (price on request). Prices checked on 26 Oct 2026.

Does AnythingLLM have an API?

Yes. The maker’s pages state that AnythingLLM has an API. Read on the maker’s pages on 18 Nov 2026.

Which platforms does AnythingLLM run on?

AnythingLLM runs on Web, macOS, Windows, Linux, Android, Browser extension and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.

Is AnythingLLM open source?

Yes. The code of AnythingLLM is published at github.com/Mintplex-Labs/anything-llm under the MIT licence. Read on the maker’s pages on 18 Nov 2026.

Is AnythingLLM still available?

Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that AnythingLLM has ended.

What changed recently in AnythingLLM?

The latest entry in its maker’s changelog: 26 Oct 2026, “AnythingLLM v1.19.0”. Before it: 13 Oct 2026, “AnythingLLM v1.18.0”. Changelog checked on 17 Nov 2026.

Sources

Not confirmed

Latest change
The official v1.20.0 changelog page lists changes but does not show a publication date.
Official website