meetily vs rowboat
Privacy-first meeting note-taker that runs 100% on-device: live Whisper/Parakeet transcription, speaker diarization, local Ollama summaries. Desktop app for macOS & Windows — no cloud, no call bots. — versus — Desktop AI coworker (YC S24) that indexes email, meetings and Slack into a living backlinked knowledge graph, then acts on it — email client, browser, meeting notes, background agents, code mode.
Overlapping on the meeting slice: Meetily is the dedicated local meeting note-taker; Rowboat bundles an equivalent mic+speaker transcriber whose summaries feed its knowledge graph rather than standing alone.
| meetily | rowboat | |
|---|---|---|
| Stars | 25k | 17k |
| Forks | 2.6k | 1.6k |
| Language | Rust | TypeScript |
| License | MIT | Apache-2.0 |
| Last activity | 1 months ago | today |
| Topics | local, voice | agents, memory |
| Curated connections | 2 | 3 |
meetily — the curator's take
The default pick when meeting content must not leave the machine — legal, health, finance, anything under NDA: transcription (Whisper/Parakeet + Sortformer diarization) and summarization (Ollama) both run locally, and it captures system audio directly instead of injecting a bot into the call, so it works with any meeting app. NOT a team product: notes live on one desktop — no shared workspace, no CRM hooks — and summary quality is capped by whatever model your hardware can run. If you want a searchable team archive and don't mind the cloud, a hosted note-taker will serve better. Budget real RAM/CPU; live diarization on a weak laptop will struggle.
rowboat — the curator's take
The thesis is memory that compounds vs retrieval that starts cold: everything you touch gets indexed into an Obsidian-style backlinked graph stored as plain local Markdown — inspectable, editable, yours — and the work surfaces (email client that drafts replies with full context, isolated browser, local meeting transcriber, event/schedule-triggered background agents) all read from it. Code mode drives Claude Code or Codex with that context. BYO model including Ollama. Use it if you want one desktop app to BE the AI layer over your work life. When NOT: it's maximalist by nature — email + browser + meetings + code in one young app means breadth outruns polish in places, and Google-service setup is a manual OAuth dance. Data stays local; that part they got exactly right.