Appearance
FeynmanLM vs Heptabase
Heptabase is a visual thinking tool: whiteboards and cards for mapping out complex topics, with PDF annotation, a Zotero workflow, and a growing credit-based AI layer including an AI tutor. It's one of the best sense-making canvases available. FeynmanLM shares its local-first values but works the other way around: instead of you arranging knowledge spatially, it tracks the sources you consume and verifies — through Feynman-style AI review — that you understood them.
At a glance
| FeynmanLM | Heptabase | |
|---|---|---|
| Price | $29 one-time (launch price, regular $67), 7-day trial | No free tier. Pro $107.88/yr; Premium $215.88/yr; Premium+ $647.88/yr (monthly billing higher) |
| AI costs | Pay-as-you-go: free with your existing AI subscription via MCP, or your own API key at list price | Credit-metered: 100 credits/mo on Pro (Gemini only), 1,800 on Premium; no bring-your-own-key |
| AI tutor | Feynman-technique review with any MCP assistant or in-app Chat — included | AI tutor requires Premium ($215.88/yr) |
| Platforms | Native macOS app (macOS 14+) | Mac, Windows, Linux, iOS, Android, web |
| Data storage | Local SQLite + files in your private iCloud container, CloudKit sync | Local-first database; sync via Heptabase's AWS cloud (US, not end-to-end encrypted) |
| Source ingestion | Automatic: Safari reading list, Apple Podcasts, PDFs, papers, books, YouTube, X posts | Manual: PDF import, web clipper, YouTube transcripts, Zotero, Readwise |
| Podcasts | Follow shows, full episode transcripts | Not supported |
| Spaced review | Weekly Schedule + saved Feynman review history per source | On the roadmap, not shipped |
| Export | Files in your iCloud Drive; SQLite you can open | Strong: full Markdown + JSON export, automatic daily local backups |
Pricing verified July 2026 (Heptabase's May 2026 price list) — check heptabase.com/pricing for current numbers.
Pricing: metered credits vs pay-as-you-go
Heptabase has no free tier and its AI is credit-metered. The plan most learners would want — unlimited PDFs plus the AI tutor and non-Gemini models — is Premium at $215.88/yr billed annually ($23.99 month-to-month). Heavy AI use points to Premium+ at $647.88/yr. There's no bring-your-own-key escape from the meter.
FeynmanLM is $29 one-time at launch pricing. AI review runs through the subscription you already have (Claude, ChatGPT, Gemini, Grok via MCP) at no extra cost, or through your own API key at raw provider list price — the app records every token and shows costs to the cent. Three years of Heptabase Premium is ~$648; three years of FeynmanLM is $29 plus AI usage you control.
Where Heptabase is better
- Visual sense-making. Whiteboards, spatial card arrangement, and journals are a genuinely different way to work through hard material. FeynmanLM has no canvas.
- Cross-platform. Mac, Windows, Linux, iOS, Android, and web. FeynmanLM is Mac-only.
- Note-taking depth. Heptabase is a full PKM app; FeynmanLM deliberately isn't one.
- Academic PDF workflow. Annotation, OCR parsing (Premium), and Zotero integration are strong for paper-heavy research.
- Exemplary export. Automatic daily Markdown + JSON backups on your own disk set the standard for exit-friendliness.
Where FeynmanLM is better
- The retention loop exists today. Heptabase's spaced repetition has been on the roadmap for years and remains unshipped; its AI tutor is a guided-session feature on the $215.88/yr tier. FeynmanLM ships the whole loop — weekly Schedule, Feynman-technique review, per-source understanding history — for $29 once. See Why Quizzing?
- No AI meter. Credits are a second subscription inside the subscription. FeynmanLM never meters or marks up your AI — your existing assistant via MCP is free to use, your API key is billed by the provider, not by us.
- Sources arrive automatically. Heptabase ingestion is pull-based: clip, import, drag. FeynmanLM discovers sources from your Safari reading list, Apple Podcasts follows, iCloud folders, and reference managers.
- Podcasts. Full episode transcripts as first-class study sources; Heptabase has no podcast pipeline.
- Model freedom at every price. Heptabase locks non-Gemini models behind Premium. FeynmanLM works with Claude, ChatGPT, Gemini, or Grok from day one.
- Sync through your own cloud. Both apps are local-first, but Heptabase syncs through its US-based AWS (readable by the vendor); FeynmanLM syncs through your personal iCloud account, and its servers never store your library.
Which should you choose?
Choose Heptabase if your bottleneck is making sense of complex material and you think spatially — or you need Windows, Linux, or Android.
Choose FeynmanLM if your bottleneck is remembering what you consume: you want automatic source capture (podcasts included), a scheduled review loop that exists today, and AI costs that stay at provider price instead of climbing credit tiers.
Some people use both: Heptabase to map a topic while learning it, FeynmanLM to track the sources and verify the understanding sticks.