anything-llm
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
claude mcp add --transport stdio mintplex-labs-anything-llm docker run -i mintplex-labs/anything-llm
How to use
AnythingLLM is a versatile full-stack application that allows users to interact with various documents and resources through AI-powered chat. Users can create 'workspaces' that encapsulate specific documents, enabling focused conversations without cross-contamination of context. The application supports multiple LLMs and vector databases, allowing users to choose their preferred AI model for generating responses. Additionally, it features a no-code AI agent builder, making it accessible for users without programming skills to create custom AI agents tailored to their needs.
How to install
To install AnythingLLM, ensure you have Docker installed on your machine. Then, follow these steps:
- Pull the Docker image:
docker pull mintplex-labs/anything-llm - Run the Docker container:
docker run -i mintplex-labs/anything-llm - Access the application through your web browser at the designated local URL provided in the terminal output.
Additional notes
Make sure to check the documentation for specific environment variables that may need to be configured for optimal performance. Common issues include Docker not running or insufficient memory allocated to the Docker container. For multi-user support, ensure that your Docker instance is properly configured to handle multiple connections.
Related MCP Servers
mcp-agent
Build effective agents using Model Context Protocol and simple workflow patterns
tome
a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP
dexto
A coding agent and general agent harness for building and orchestrating agentic applications.
web-search
A simple, locally hosted Web Search MCP server for use with Local LLMs
openapi
OpenAPI definitions, converters and LLM function calling schema composer.
packt-netops-ai-workshop
🔧 Build Intelligent Networks with AI