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

Fieldcard: I built a local AI that prints you a field card and gets you outside in 30 seconds

Description and use

Fieldcard enables offline, zero‑screen, print‑first outdoor planning, generating a safe, data‑rich A5 card in under 30 seconds without exposing location data or incurring costs.

Problem

Users want a quick, offline tool to generate a printable outdoor exploration card that includes a mission, map, sensory prompts, and safety data without relying on cloud services.

Outcome

Fieldcard enables offline, zero‑screen, print‑first outdoor planning, generating a safe, data‑rich A5 card in under 30 seconds without exposing location data or incurring costs.

Workflow

  • 1. Run python fieldcard.py --lat <lat> --lon <lon> --minutes <minutes> --activity <mode> or start the local web UI with python fieldcard.py serve
  • 2. The script queries Overpass for nearby places, iNaturalist for local species, Open‑Meteo for weather, and NOAA for sunset/turn‑around calculations
  • 3. Facts are passed to the local LLM which writes the mission title, paragraph, and nine sensory prompts
  • 4. Code renders an A5‑size HTML card with map, bingo grid, weather, and safety warnings
  • 5. User prints the card and goes outside without using the phone

Evidence

Fieldcard is a single-command tool that turns "I have 90 minutes" into a one-page printable A5 field card.

Source

The screen is the shortest part. That's the point.

Source

The local open-weight model (default: llama3.2:3b via Ollama) writes only the words — the title, the mission paragraph, and the nine sensory prompts.

Source

The code handles everything safety-critical: sunset time (NOAA solar equations), turn-around time, reach radius, daylight warnings.

Source

On the trail, in a park with patchy signal, or on a plane — the card generates regardless.

Source

The card stayed in my pocket for the whole walk. The phone didn't come out once.

Source

  • Record date: 2026-10-11T15:55:59.567Z