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 | Free to download — no free tier to outgrow, because there are no tiers | No free tier. Pro $107.88/yr; Premium $215.88/yr; Premium+ $647.88/yr (monthly billing higher) |
| AI costs | Prepaid balance ($5 free to start): any model in Chat at provider API price +15%, or 1¢ per tool call via the AI subscription you already pay for | 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 — no tier required | 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: credit tiers vs metered usage
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. The credits are Heptabase-denominated, they reset every month whether you used them or not, and there's no bring-your-own-key escape from the meter.
FeynmanLM is free to download, and there is no plan to pick — you top up a prepaid balance and spend it on the AI you actually run, starting with $5 free. Two ways to spend, mixable: any model in the in-app Chat, billed at that provider's own API list price plus a 15% margin on the exact cost the provider reports; or the Claude, ChatGPT, Gemini, or Grok subscription you already pay for, connected over MCP at 1¢ per tool call — your subscription covers the inference, the cent covers reading and writing your library, and a daily spend cap keeps a runaway agent from surprising you. Either route also spends a little on background work — transcript cleanup, paper metadata extraction, search embeddings — billed the same way, with the model configurable per task. The app records every token and shows costs to the cent.
The three-year comparison is lopsided in a way that's worth stating plainly: Heptabase Premium is ~$648 before you've done anything, while FeynmanLM's floor is $0 and the meter only moves when you use it.
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 — with nothing to unlock and nothing to buy. See Why Quizzing?
- No credit tiers. Credits are a second subscription inside the subscription, denominated in Heptabase's own currency and refilled monthly whether you need it or not. FeynmanLM bills against real provider costs instead: API list price plus 15% for in-app Chat, or a flat 1¢ per tool call if you drive it from an assistant you already subscribe to. No feature is gated behind which tier you're on.
- 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 track what you actually used 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.