Prairies: Find your inner peace one quest at a time

Description and use

Touch Grass is an offline-first walking companion that prepares routes, records voice notes, transcribes locally with Whisper, cleans text with Gemma, and stores data locally with optional cloud backup in MongoDB Atlas.

Problem

Users want a reason to go outside without relying on constant network connectivity or sending voice recordings to remote AI services.

Outcome

Touch Grass enables offline walking quests with local voice transcription and text cleanup, preserving privacy and reducing reliance on cloud services while providing optional lightweight cloud backup.

Workflow

• Open Touch Grass
• Choose a walking area or use the current location
• Prepare a quest
• Start the walk
• Record a voice note at a stop
• Let Whisper transcribe it locally
• Let Gemma clean the transcription when supported
• Finish the walk and review the journal

Evidence

Touch Grass is an offline‑first walking companion that turns a short walk into a small reflective quest.

Source

The app prepares a street‑routed walking loop while the user is online. Once the quest is ready, the user can walk without a connection, visit suggested places, record voice notes, take a photo, and later review the experience as a journal.

Source

Whisper runs locally in the browser through WebAssembly. It converts a voice note into a transcript without uploading the audio.

Source

The formatted journal entry is produced by an on‑device language model. The cleanup prompt asks Gemma to preserve the speaker's meaning, fix punctuation and capitalisation, remove filler words, and return only the cleaned text.

Source

MongoDB Atlas stores separate documents for walks, stops, entries, and reports. Each record is associated with a device ID, so one installation cannot overwrite another installation's records.

Source