A finished research run on an example topic, shown in full — the findings, the sources behind them and the product versions are all the run's own output, except that a product name may have been changed where it matched an existing brand.

Back to the run overview AI meeting notes

Experimental

Consensus Protocol

An open local data standard and lightweight sync engine that lets any local-first notetaker (Meetily, Hyprnote, or the many solo repos) export to a shared format, enabling interoperability across the fragmented open-source ecosystem.

01

What to build

  • MVP

    A published open schema plus a reference CLI/library that converts output from three or four popular local notetaker repos into one common JSON transcript+diarization format, with a simple local search index built on top.

  • Why it can be better

    The open-source scene is a long tail of single-maintainer, single-OS repos with no shared format, so users accumulate disconnected local histories; a shared standard turns fragmentation into an interoperable ecosystem rather than requiring one company to rebuild every capture mode itself.

  • Revenue model

    Open-core model: the standard and CLI are free, with a paid hosted (still local-encrypted) sync and search app for teams wanting cross-device consolidation.

  • Target user

    Developers and privacy-focused power users already running open-source local notetakers who want their tools to interoperate.

02

Context

The opportunity this answers

Build a local-first meeting-memory layer for professionals that unifies transcripts from any notetaker or capture mode into one private, searchable history.

Why now

A wave of open-source local-first notetakers built on Rust/Swift/Tauri has already proven demand for on-device processing, with diarization and Whisper models now standard, high-download building blocks anyone can bundle, while search interest for generic 'AI meeting notes' has plateaued — signaling the crowded cloud tier is saturated even as privacy-driven local alternatives keep multiplying, and none of them yet unify capture contexts, ingest rival platforms' exports, or sync back out privately.