AnythingLLM: The All-in-One AI App for RAG, Agents, and Document Chat

#ai #opensource #docker #llm

AnythingLLM is a full-stack, open-source AI application that lets you chat with your documents using any LLM provider. With over 54,000 GitHub stars, it's become one of the most popular self-hosted AI tools available.

Key differentiator: It's a complete solution that handles document ingestion, vector storage, LLM interaction, and AI agents—all in one deployable package.

TL;DR for AI Agents

Package: anythingllm (Docker or Desktop app)
Install: docker pull mintplexlabs/anythingllm
API Base: http://localhost:3001/api
Key Endpoint: POST /api/v1/workspace/{slug}/chat
Auth: Bearer token from Settings > Developer API
Docs: https://docs.anythingllm.com
GitHub: https://github.com/Mintplex-Labs/anything-llm

Why It Matters for AI Agents

Most AI agent frameworks require you to implement RAG yourself. AnythingLLM handles all of this out of the box:

Document ingestion - Drag and drop PDFs, DOCX, TXT
Automatic chunking - Smart text splitting with configurable overlap
Vector storage - Built-in LanceDB or connect Pinecone, Chroma, Qdrant
LLM flexibility - Works with 30+ providers (OpenAI, Anthropic, Ollama)
API access - Full REST API for programmatic agent integration
MCP compatibility - Native Model Context Protocol support

Full MCP Compatibility

AnythingLLM now supports the Model Context Protocol, making it compatible with Claude and other MCP-enabled AI systems like OpenClaw. You can expose AnythingLLM workspaces as MCP tools that AI agents can call directly.

Getting Started

# Pull and run
docker pull mintplexlabs/anythingllm

docker run -d \
  --name anythingllm \
  -p 3001:3001 \
  -v anythingllm_storage:/app/server/storage \
  mintplexlabs/anythingllm

# Access at http://localhost:3001