Pagdandi: an open trek database that gets the group chat onto an actual trail

Description and use

Pagdandi cuts trek planning time to minutes by providing sourced recommendations, audio intros, a one‑page plan, and daily weather/news emails.

Problem

Group chats often stall when deciding on a trek because of differing budgets, experience levels, and lack of a quick, reliable recommendation.

Outcome

Pagdandi reduces planning time from hours to minutes, ensures fact‑based recommendations, and provides daily operational support, improving group readiness and experience.

Workflow

• 1. User inputs group size, experience, budget, days, month, and starting location into the guide.
• 2. Guide (Gemma 4 via Ollama) processes the query and returns ranked trek cards from the database.
• 3. User selects a trek; the page shows sourced facts, altitude warnings, and a one‑page printable plan.
• 4. User downloads audio intro and prints the plan.
• 5. User signs up for daily updates with travel date; the system sends weather, news, and daily to‑do emails until departure.
• 6. After trip, data remains open for future groups to improve the database.

Evidence

Pagdandi is an open database of 20 Indian treks, every fact sourced, with a trek guide that runs on Gemma on a laptop.

Source

Tell it how many of you there are, who has trekked before, the budget, the days, the month and where you're starting from, and it recommends treks you can actually do, from 20 well‑known Indian treks with every fact sourced.

Source

Running your own takes about 10 minutes, plus the model download: brew install ollama postgresql@17 pgvector node@24 pnpm ...

Source

Get daily updates. Sign up with the travel date and get one email a day until you leave: the forecast at the road head and the high point, the week's headlines with links, and one thing to do outside today.

Source