Verified project record

Mintplex-Labs/anything-llm

This application lets users chat with their documents and run AI agents in a private, locally hosted environment by default. It supports multi-user permissioning, dynamic model routing, and custom agent construction without requiring coding skills.

Project overview

Project type: AI Agent · RAG · Workflow
Use cases: Chat Assistants
Deployment: Docker / Docker Compose
License: MIT

Best for

General users and developers who need a locally runnable, hyper-configurable AI workspace for document chat and agent automation without writing code.

Key capabilities

Ingest documents including PDF, TXT, and DOCX and interact with them via a chat UI that provides source citations and supports drag-and-drop uploads.
Automate workflows using built-in agents capable of browsing the web and utilizing no-code AI Agent builder flows.
Supports multiple users with per-user access control and permissioning without compromising instance security or privacy.
Automatically routes chats to designated providers and models based on user-defined rules.
Allows the language model to remember important information about the user or the workspace.
Run recurring tasks or prompts on a cron schedule with full agent capabilities.
Enables unlimited tools for models while reducing token usage by up to 80% per query.
Compatible with the Model Context Protocol (MCP).

Limitations and risks

Telemetry is optional but includes PostHog integration, which requires an external service.
GPU requirements and minimum hardware specifications are not documented.

Getting started

Download and run the provided desktop application for Mac, Windows, or Linux to run the application locally by default.

Evidence and sources

README: 👉 AnythingLLM for desktop (Mac, Windows, & Linux)! <a href="https://anythingllm.com/download" target="_blank"> Download Now</a>
README: AnythingLLM is the all-in-one AI application that lets you build a private, fully-featured ChatGPT—without compromises. Connect your favorite local or cloud LLM, ingest your docum…
README: Intuitive chat UI with drag-and-drop uploads and source citations.
README: **Vector Databases:** - [LanceDB](https://github.com/lancedb/lancedb) (default)
README: - [Dynamic Model Routing](https://docs.anythingllm.com/model-router/overview) - Automatically route chats to the best provider & model for the conversation based on rules you defi…

Reviewed at: 2026-07-17T05:58:16Z