FeynmanLM Docs

Appearance

FeynmanLM ​

The problem ​

You read articles and papers. You listen to podcasts and read books. All of this to make sense of the world, but just throwing stuff at the wall and seeing what sticks is not an effective way to remember any of it.

The research is clear: quizzing yourself is the single most effective way to learn. Not re-reading, not highlighting, not summarizing. Actively testing your recall. And the Feynman Technique takes this further: if you can't explain something simply, from scratch, you don't actually understand it.

But there's a second problem beyond retention: tracking all your content. As Andy Matuschak explores in How Might We Learn?, the tools we use for learning are far behind the tools we use for everything else. You consume across dozens of sources and formats, and none of it is connected.

How FeynmanLM fits in ​

Today, learning and research is fragmented across a stack of disconnected tools: reference managers (Paperpile, Zotero), reading lists (Matter, Pocket), note-taking apps (Notion, Obsidian), and flashcard apps (Anki, Mochi). None of them talk to each other, and none of them were designed for how we actually learn.

FeynmanLM brings all your sources into one place and makes them easy to use with AI assistants like Claude, ChatGPT, Gemini, and Grok. Your AI assistant can see your sources, quiz you on them using the Feynman technique, and help you make connections across everything you've read.

The workflow is simple:

  1. Track sources in the Studio tab — articles, papers, podcasts, books, and more flow in automatically from your browser reading lists, local files, and integrations.
  2. Drag sources into your AI — select sources in Studio, then drag them into Claude, ChatGPT, Gemini, or Grok. No setup required.
  3. Learn through dialogue — ask your AI to test you, probe your understanding, and challenge your explanations using the Feynman technique and Socratic dialogue.

For a persistent connection where your AI can search your entire library without dragging, you can optionally set up an MCP server via Tailscale.

All data lives in your private iCloud container: no servers, no accounts, fully encrypted.

FeynmanLM on macOS

Track your sources:

Use with AI:

  • Drag & Drop: drag your sources into Claude, ChatGPT, Gemini, or Grok — no setup needed
  • Setup MCP Server: optional persistent connection via Tailscale for full-library access
  • Learning with MCP: how to use AI for Feynman technique review and Socratic dialogue