Plain-AyI
← All projects
Documents & knowledge

LightRAG

Lets AI answer questions about your documents by building a map of the people, ideas and links inside them.

Research-backed

What it does

RAG (retrieval-augmented generation) means the AI looks things up in your own documents before it answers. LightRAG is a research project that adds a "knowledge graph" to this: a map of the key things in your documents and how they connect.

Its makers say this helps answer questions that need several pieces of information joined together. It can cite sources, handle images and tables through other tools, and lets you delete documents and update the map.

It includes a web interface for adding documents, asking questions and seeing the knowledge map. It works with many storage systems and AI models.

Who it's for

Developers and researchers building question-answering tools over large document collections.

Can I use it without coding?

With some setup. The server installs with a few commands and has a web interface, but you need to configure AI model and storage settings. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Mac, Windows, Linux, Server
Privacy
Your choice: run it on your device or use an online service
API key
Not needed

Try it

  1. Install the LightRAG server with Python's package tools, or run it with Docker.
  2. Edit its settings file to choose your AI model and embedding service.
  3. Start the server and use its web interface to add documents and ask questions.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it