Who it is forA student or analyst with a pile of papers, articles and recordings to make sense of.
The problemReading and cross-referencing dozens of sources by hand takes days, and general chatbots do not cite your files.
The outcomeAnswers grounded in your notebook that cite the sources, notes and insights they used.
What you need first
- Docker Desktop (macOS, Windows) or Docker Engine with the Compose plugin (Linux)
- An API key from an AI provider, or a local model server such as Ollama
- At least one language model and one embedding model configured in the UI
Steps
- Open Models in the sidebar and click Add Configuration for your provider (or a Base URL for Ollama)
- Click Test, then add at least one Language model and one Embedding model
- Click Auto-assign Defaults
- Create a notebook, add PDFs, videos, audio or web pages, and start chatting
Prompt for your agent
In lfnovo/open-notebook, connect <provider or Ollama>, create a notebook for <topic>, add <sources>, and ask <question>. Show which sources each answer cites.
Caveat. This card is written from the lfnovo/open-notebook README, not from a test run by Deduped. Before you start, make sure you have Docker Desktop or Docker Engine with the Compose plugin. Check the repo for newer instructions before you rely on these steps.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for lfnovo/open-notebook and "Chat with your PDFs and web pages and get cited answers"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer