AnythingLLM

Active
GitHub JavaScript MIT

Description

AnythingLLM is an all-in-one AI productivity app with a self-hosted chat UI, RAG knowledge base, AI agents, and multi-model management, privacy-first with zero configuration.

Key Features

  • Multi-model support — Supports 30+ LLM providers including OpenAI, Anthropic, Ollama, LM Studio, and local llama.cpp models
  • Dynamic model routing — Automatically routes conversations to the best provider and model based on user-defined rules
  • AI Agent builder — No-code AI Agent builder with built-in tools like web browsing and MCP protocol compatibility
  • Multi-user & permissions — Docker version supports multi-user instances with per-user access control and experience management
  • Embeddable chat widget — Custom embeddable chat component for websites with drag-and-drop document upload and source citations
  • Intelligent skill selection — Enables unlimited tools for models while reducing token usage by up to 80% per query

Use Cases

💡 Build a private ChatGPT alternative with local LLM deployment to protect data privacy
💡 Import company documents into a knowledge base for intelligent Q&A based on internal materials using RAG
💡 Embed AI customer service components on websites with document upload and multi-turn conversation support
💡 Automate complex workflows with AI Agents such as web data collection and information summarization
💡 Integrate AnythingLLM into existing business systems via API for intelligent document processing

Tags

chatbot rag knowledge-base local-llm mcp javascript

Categories

💬 Chat UI ⚡ Agent Tools

Quick Start

docker pull mintplexlabs/anythingllm
docker run -d -p 3001:3001 \
  --cap-add SYS_ADMIN \
  -v /path/to/storage:/app/server/storage \
  -v /path/to/collector/hotdir:/app/collector/hotdir \
  mintplexlabs/anythingllm

# Then open http://localhost:3001 to configure your LLM and upload documents
Visit GitHub Visit Website View Docs

Related Projects