An open-source AI note-taking app in the Granola mould, written in Rust — meeting notes captured and structured by a model, without the notes leaving a proprietary product.
The problem
AI note-taking is one of the few genuinely useful consumer applications of language models, and almost all of it is closed. Your meetings are among the most sensitive text you produce, and they end up on someone else’s servers by default.
How it works
- An open-source alternative to the Granola model of AI note-taking, MIT-licensed so the whole pipeline can be read and changed.
- Written in Rust — the choice matters for a desktop capture tool, where a persistent background process has to stay cheap and stable.
Why it exists
The same argument as PrometheusAI, one domain over: if the data is personal, the software handling it should be inspectable.
More work
Hiring for AI or ML?
I am open to AI/ML Engineering, Data Science, and Python roles, plus research collaborations and consulting. New York based, shipping worldwide.