# Fugleramme — an e-ink frame that names the birds it hears

> A Raspberry Pi frame that turns the birds singing outside your window into a 19th-century natural history plate.

- Org: Arne Giacomo Munthe-Kaas
- Date: 2026-09-14
- Category: showcase, repo
- Source: https://github.com/arnegiacomo/fugleramme
- Canonical page: https://ai-tldr.dev/releases/arnegiacomo-fugleramme/

## In short

Fugleramme is a Raspberry Pi picture frame that listens for birdsong, identifies the species with a local BirdNET-Go model, and redraws the birds on an e-ink panel as hand-cut 1800s illustrations. No cloud, MIT-licensed.

## What it is

Fugleramme pairs an always-on microphone with a 13.3-inch Inky Impression e-ink panel and repaints the display with whichever birds it just heard. The artwork is not generated: the project ships more than 800 cut-outs from public-domain natural history plates, covering over 400 species, with the best coverage across the Nordics, the British Isles and Germany. Arne Giacomo Munthe-Kaas released v0.21.3 on 14 September 2026 and the project reached the top of Hacker News the next day with 1,801 points.

## How it works

Species identification runs on BirdNET-Go, the audio classifier from the Cornell Lab of Ornithology and Chemnitz University of Technology, entirely on the Raspberry Pi 5. Each detected species is matched to its illustration, background-removed, then packed onto a textured paper page with the larger birds placed toward the centre and sized by body mass. Because e-ink costs power only when it changes, the frame redraws only when the set of birds changes.

## Why it matters

An always-on listener that never uploads audio is a good argument for small local models: the whole pipeline fits on a Raspberry Pi and keeps a live microphone off the internet. The e-ink panel is also optional — a web-only mode runs the same detection on other displays — so the code is a usable starting point for anyone building a quiet, offline sensing appliance.

## Who it's for

Raspberry Pi tinkerers and birdwatchers

## Try it

docker run -d -p 8080:8080 -v fugleramme:/data ghcr.io/arnegiacomo/fugleramme

## Links

- [GitHub Repo](https://github.com/arnegiacomo/fugleramme)
- [Project Page](https://arnegiacomo.dev/fugleramme/)
- [Release v0.21.3](https://github.com/arnegiacomo/fugleramme/releases/tag/v0.21.3)