AnythingLLM
AnythingLLM is an application for chatting with documents and automating complex workflows with AI Agents.
Verified
Core facts
Read by a script from the official API, not rewritten by a model.
- License
- MIT
- Languages
- JavaScript
- Maintainer
- Mintplex-Labs
- Homepage
- https://anythingllm.com
- Verified
What it is
AnythingLLM is an application for chatting with documents and automating complex workflows with AI Agents. AnythingLLM by Mintplex Labs Inc contains a telemetry feature that collects anonymous usage information. The monorepo consists of six main sections. This project is MIT licensed.
Main features
The built-in local LLM engine, powered by Lemonade and llama.cpp, runs local models on a CPU or GPU (NVIDIA via CUDA, AMD and Intel via Vulkan).
Scheduled Tasks run recurring tasks or prompts on a cron schedule with full agent capabilities.
Automatic & User Managed Memories let the LLM remember important information about the user or the workspace.
MCP-compatibility is listed among the features.
A no-code AI Agent builder is listed among the features.
Getting started
AnythingLLM is available for desktop on Mac, Windows, and Linux.
For development, a setup script run from the root of the repo fills in the required env files for each application section.
A server development script run from the root of the repo boots the server locally.
A frontend development script run from the root of the repo boots the frontend locally.
A collector development script run from the root of the repo runs the document collector.
AnythingLLM Mobile (Android) is open source.
Who it is for
Multi-user instance support and permissioning are Docker version only. The custom embeddable chat widget for a website is Docker version only. Agents inside the workspace can, for example, browse the web.
AnythingLLM supports multiple document types, such as PDF, TXT, and DOCX. AnythingLLM provides a chat UI with drag-and-drop uploads and source citations. Generic OpenAI-compatible embedding APIs are listed among the embedder models.
Among the embedder models, AnythingLLM Native Embedder is marked as default. Among the vector databases, LanceDB is marked as default. The collector section is a NodeJS express server that processes and parses documents from the UI.
The docker section holds Docker instructions, the build process, and information for building from source. The embed section is a submodule for generation and creation of the web embed widget. The browser-extension section is a submodule for the chrome browser extension.
Setting the telemetry-disable variable to true in the server or docker env settings opts out of telemetry. Telemetry can also be disabled in-app through the Privacy item in the sidebar. The project states that no IP or other identifying information is collected by telemetry.
The telemetry provider is PostHog, an open-source telemetry collection service. The project states that the anonymous data is never shared with third parties. AnythingLLM Browser Extension is a browser extension that allows using AnythingLLM in the browser.
AnythingLLM Embed is a widget that allows embedding AnythingLLM in a website.
Related tools
Related tools listed on this site.
EveryGen AI
Video generator and creative studio describing scene planning, clips, image editing, voices, music and video assembly.
QwenPaw
Personal AI assistant and agent workstation running in your own environment. Its primary description presents local/cloud deployment, multiple channels and extension through Skills and MCP.
Cursor
A coding agent for understanding repositories, planning features, changing code, and reviewing diffs.
CodeBuddy IDE
AI coding workspace for product, design and development. Its dedicated IDE documentation describes technical conversations, code completion, Figma-to-code, diagnostics and a design-to-deployment workflow.
InfCode
Enterprise AI coding agent from TokensInfinity. Its site describes using enterprise code and knowledge through IDE, extension and CLI forms for completion, cross-file changes and engineering tasks.
阿里云百炼
Alibaba Cloud Bailian is a model-service and application-development platform for model inference, knowledge bases, agents and workflows.
千问云
The discovered Qianwen Cloud entry currently presents the Qianwen AI Platform for model discovery, online trials, API access, Skills/CLI tooling and usage/cost management.
Figma AI
Collection of AI workflows and capabilities within Figma products for design exploration, content editing and connecting prototypes with code.
Pixso AI
AI design capability integrated into the Pixso canvas. Its official page describes generating editable web and mobile interfaces from text, sketches or screenshots and continuing to refine existing designs.
Ardot
AI design and collaboration tool. Its official site describes text/image-to-editable UI, vector editing, dynamic layouts and design systems, plus collaboration, annotations and design-to-development handoff.
纳米AI
Nano AI is an AI search and agent assistant whose site says it can generate videos, reports and slides from one sentence and integrates several large models.
Exa AI
Exa is a web-retrieval service for AI applications and agents, describing search, content retrieval, deep research and structured-output APIs.
Sources
This page is written from the official sources below. Open them to check the original text.
- GitHub READMEhttps://github.com/Mintplex-Labs/anything-llmFetched
Verified ·
This page is written by AI from the official sources above and checked automatically. This site has not tested it. Found a mistake? Tell us.