back to home

steveyeow / Feynman

Read books the way Feynman did — along with a continuously evolving network of agent-simulated great minds

127 stars
6 forks
1 issues
JavaScriptPythonHTML

AI Architecture Analysis

This repository is indexed by RepoMind. By analyzing steveyeow/Feynman in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.

Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.

Source files are only loaded when you start an analysis to optimize performance.

Embed this Badge

Showcase RepoMind's analysis directly in your repository's README.

[![Analyzed by RepoMind](https://img.shields.io/badge/Analyzed%20by-RepoMind-4F46E5?style=for-the-badge)](https://repomind.in/repo/steveyeow/Feynman)
Preview:Analyzed by RepoMind

Repository Overview (README excerpt)

Crawler view

Feynman > "You learn by asking questions, by thinking, and by experimenting." — Richard Feynman **Chat with books. Great minds join in.** With Feynman, you can chat with the books you want to read to quickly understand them and explore the broader context around them. You can also start from a topic, and Feynman will surface the most relevant books to help you build a knowledge system grounded in them. As you chat, a continuously evolving network of agent-simulated great minds — scholars, scientists, practitioners — automatically join the conversation, so you read, learn, and discuss ideas together with the most relevant thinkers. What makes this different: • **Knowledge beyond the page** — a four-layer content system (RAG → Content Fetch → Web Search → LLM Knowledge) means answers draw on the book's text, metadata from Open Library/Google Books/Wikipedia, real-time web results, and the model's own training — not just what's printed on the page. • **A library that grows as you chat** — there's no static catalog. Books are discovered through topic exploration, search, chat mentions, uploads, and community voting. Every book title mentioned in a conversation gets added automatically. • **An evolving network of great minds** — great minds accumulate memory from conversations, becoming richer and more nuanced over time. You can upload your own minds — or anyone you admire — from a Twitter profile, blog, or text to connect and expand the scope of the network. Why I built this Feynman is **not** a replacement for reading. I'm a devoted paper-book lover — the tactile act of flipping through physical pages puts me in a near-meditative state, and nothing replaces that. Richard Feynman rarely read a book cover to cover — he approached books with questions, pulled insights from multiple sources, and moved on when a book had nothing left to teach him. I read the same way. When I want to explore a new domain, I need to know *which* books are worth the deep read and how they fit together. This tool helps me: • **Scout before committing** — quickly understand what a book covers and whether it deserves my full attention. • **Build a knowledge scaffold** — when I'm entering an unfamiliar field, it synthesizes key ideas across multiple authoritative works so I can form an initial mental map before diving in. • **Go beyond the text** — imagine sitting down with the author for a few hours; you'd learn far more than what's on the page. Feynman gives you that experience — because the AI draws on broader knowledge related to the book, every conversation surfaces valuable context and insights you wouldn't get from reading alone. In short: Feynman helps you read the way Feynman did — not replace reading itself. Beyond books In 1985, Steve Jobs said: *"Someday, some student will be able to not only read the words Aristotle wrote, but ask Aristotle a question and get an answer."* That idea stuck with me. Every book is a window into a great mind — but a great mind is far more than any single book. If you could actually sit down with Aristotle, or Feynman, or Adam Smith, you'd get something no book alone can give: their way of thinking, applied to your questions. So I'm also trying to build a continuously evolving network of agent-simulated great minds. They join your reading sessions, challenge your assumptions, and bring perspectives you'd never find on your own. You can also upload your own minds into the network to connect and expand the scope of collective wisdom of human thought. --- Feynman is a Socratic study companion powered by AcademiAI. It does three things: **1. Turn any book into a conversation** — Ask questions and get answers grounded in the book's actual content, with every claim traced back to a specific passage. But it doesn't stop at the text — a four-layer content system (RAG, Content Fetch, Web Search, LLM Knowledge) brings in broader context and related knowledge, so you learn more than the book alone could teach you. **2. Turn any topic into a knowledge system** — Curious about microeconomics but don't know where to start? Feynman discovers the right books, generates the questions you should be asking, and teaches you through conversation — all grounded in real sources, enriched by knowledge that goes beyond any single book. Every search, chat mention, and topic click adds new books to your library automatically. **3. Read and discuss with an evolving network of great minds** — As you chat, Feynman automatically invites highly relevant great minds — scholars, scientists, practitioners — to join the conversation as AI agents. These minds accumulate memory from conversations, becoming richer over time. You can also invite specific minds yourself, discover new ones through the knowledge graph, or upload your own (via a Twitter profile, blog URL, or text) to connect and expand the network. --- Chat With Books Have a book but don't want to read all 300 pages? Chat with it instead. Ask anything and get answers backed by a four-layer content system — so you always learn more than what's on the page: | Priority | Skill | What it does | |----------|-------|-------------| | 1st | **RAG** | Retrieves relevant passages from the book's indexed content | | 2nd | **Content Fetch** | Pulls information from Open Library, Google Books, and Wikipedia | | 3rd | **Web Search** | Uses Gemini Search Grounding for real-time web answers | | 4th | **LLM Knowledge** | Falls back to the model's training knowledge | Every answer includes clickable , citations — click to see exactly which passage the answer came from. No black-box responses. Select multiple books and ask questions across all of them — Feynman searches your entire library to find the most relevant passages regardless of source. Topic-Driven Knowledge Building Don't have a book? Start with a topic. There's no static catalog — your library builds itself from every conversation. Pick an interest — Psychology, Philosophy, Economics, P…