# tphakala/birdnet-go

Self-hosted realtime soundscape analyser for birds, bats and other wildlife. Multi-model local AI inference, runs 24/7 on a Raspberry Pi.

Repository: https://github.com/tphakala/birdnet-go
Canonical: https://ross.abutalabs.com/products/birdnet-go
Language: Go
License: NOASSERTION
License Family: other
Topics: audio, bioacoustics, birds, golang, tensorflow, birdnet, birdnet-pi, wildlife, birdweather, raspberry-pi, artificial-intelligence, contributions-welcome, go, linux, raspberrypi, bats, perch, self-hosted
Last push: 2026-08-26T17:23:12+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 74
- inputs: {"age_days": 1048, "days_push": 7, "days_rel": 10, "gap_med": 4.0, "n_releases_24m": 23}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1592, forks 152 (observed 2026-08-28T04:05:08.797970+00:00)

## What it is
BirdNET-Go is a self-hosted, 24/7 realtime soundscape analyser that classifies birds, bats, and other wildlife using local AI models like BirdNET, Perch, and BattyBirdNET. It ingests soundcard or network audio streams, runs multi-model inference on hardware as small as a Raspberry Pi, and presents detections, spectrograms, and heatmaps in a web UI with alerting to many notification services.

## Use cases
- identify bird species from realtime audio on a raspberry pi
- monitor bats and wildlife sounds 24/7 in my backyard
- send bird detection alerts to discord or home assistant
- run multiple bioacoustic AI models in parallel on audio streams
- self-host a bird song classifier with a web dashboard
- stream live spectrograms and detection heatmaps in the browser
- integrate bird detections with mqtt and home assistant discovery

## When to choose
- you want continuous, local wildlife sound monitoring on low-power hardware like a raspberry pi
- you need multi-model classification (birds, bats) with cross-model confidence boosting
- you want rich integrations: Discord, Slack, Telegram, MQTT, Home Assistant, webhooks, BirdWeather
- you prefer self-hosted inference without sending audio to the cloud

## When to avoid
- you need a permissively licensed tool for commercial use - the license is CC-BY-NC-SA (non-commercial)
- you only need offline batch analysis of pre-recorded files rather than realtime monitoring
- you need Windows/macOS as first-class supported platforms - it is primarily Linux/Raspberry Pi oriented

## Facets
- artifact type: application
- maturity: active
- function: audio-processing, machine-learning, llm-inference, monitoring, webhook, self-hosted
- domain: artificial-intelligence, self-hosted, iot, analytics
- platform: windows, self-hosted, go
- tags: birdnet, bioacoustics, wildlife-monitoring, raspberry-pi, soundscape-analysis, bird-detection, bat-detection, realtime-audio, home-assistant, pwa, audio, linux, macos, docker

## Member repositories
- tphakala/birdnet-go (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:08.797970+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:54:42.149433+00:00, confidence not recorded.
  - readme: https://github.com/tphakala/birdnet-go (fetched 2026-08-28T04:05:08.797970+00:00, sha d1acf724ce27)
- Data as of 2026-08-30T08:39:29.467469+00:00.