Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

A private class copilot for solo yoga teachers, powered by Gemma on their own laptop

Description and use

Saathi is a local desktop app that uses Gemma to automate class planning, student progress logging, and newsletter drafting for solo yoga teachers, keeping all sensitive data on the teacher’s machine.

Problem

Solo yoga teachers spend evenings preparing classes, writing follow‑up notes, and drafting newsletters, while also handling sensitive student health data.

Outcome

Saathi automates class prep, follow‑up, and newsletter drafting while keeping sensitive data local, reducing evening workload and eliminating external data exposure.

Workflow

  • Select class and students
  • Saathi drafts a Sanskrit/English sequence with per‑student injury callouts
  • Teacher reviews and edits the plan
  • Teacher inputs quick post‑class notes
  • Saathi writes progress logs and a follow‑up email draft
  • Saathi compiles a newsletter draft from weekly notes

Evidence

Saathi drafts a sequence in Sanskrit and English, plus a callout for every student with an injury or surgery: which poses to avoid and which modification to offer, citing their actual condition.

Source

It never sends anything itself.

Source

The student’s injuries never leave the machine. There is no server to breach, no vendor privacy policy to read, and no data‑processing agreement for a one‑person studio to sign.

Source

On my M1 Pro with 16 GB, Gemma generated at about 2 to 4 tokens per second. Without streaming, a full plan took around six minutes of staring at a spinner. With streaming, the first callouts show up after roughly a minute and the plan fills in as it is written, but the last plan I timed, for three students, still took 9 minutes 11 seconds.

Source

  • Record date: 2026-10-19T00:56:02.363Z