Find answers in the docs, browse the FAQ, or reach out directly.
Step-by-step guides for every feature — from adding content to doing a Feynman technique review.
Send us a message at [email protected]. We typically respond within 1–2 business days.
Yes. FeynmanLM uses your own AI API key (Anthropic Claude, OpenAI, or Groq) to evaluate your answers and generate flashcards. This means your data goes directly to the AI provider you choose — never through our servers. You can get keys for free at console.anthropic.com, platform.openai.com, or console.groq.com.
All flashcards, sources, and study data are stored in your private iCloud container. Data syncs between your Apple devices via iCloud and is encrypted in transit and at rest by Apple. We have no servers and never see your data. See our Privacy Policy for full details.
Anthropic Claude (Claude Sonnet, Claude Opus), OpenAI (GPT-4o and newer), Groq (fast and cost-effective), and Google Gemini (for image generation). You can mix providers — for example, use Claude for answer evaluation and Groq for speech transcription.
Yes. FeynmanLM supports voice input with real-time transcription. Choose from on-device Apple Speech (completely private), OpenAI Whisper, Groq, and other providers. Configure your preferred provider in Settings → Speech To Text.
The Apple Watch app is a companion to the iPhone app. It syncs flashcards via iCloud and supports voice-first review sessions. You cannot create cards or access the Studio from the Watch.
Download the PDF to your Mac and save it to ~/Library/Mobile Documents/com~apple~CloudDocs/Documents/articles/. The app will find it automatically when you add the paper's URL. See Adding Paper PDFs in the docs.
The MCP (Model Context Protocol) server lets Claude.ai access your flashcard knowledge base in conversations — searching cards, creating proposals, and generating explainer articles. It's optional and requires running a local server. See Setting Up the MCP Server.
After each review, you rate your recall (Got it / Again / Skip). The app schedules cards at increasing intervals based on your ratings — cards you know well appear less often, cards you struggle with come back sooner. Over time, your review queue reflects exactly what needs attention.