Our take
Activeregular commits and releases- Activity
- 81
- Community
- 51
- Issues
- 66
- Pull requests
- 83
- Merges more pull requests than 93% of the projects we track
- Releases more often than 76% of the projects we track
BirdNET-Go is an actively maintained, feature-rich self-hosted wildlife analyser, though its development is highly concentrated in one contributor and its noncommercial license limits some uses.
Good fit if
- You want continuous, local BirdNET analysis on Linux, Windows, or macOS, including Raspberry Pi hardware.
- You need multiple audio sources, optional classifiers, and configurable alerts in one application.
- Your use is compatible with the CC BY-NC-SA 4.0 license and you are comfortable operating a self-hosted service.
Look elsewhere if
- You need a permissively licensed project or intend commercial use that conflicts with its noncommercial terms.
- You want a hosted service rather than managing audio inputs, storage, and the application yourself.
- You need a project whose development is broadly distributed across its contributors.
All health signals
| Last commit | 2026-10-18 (today) |
|---|---|
| Commits, last 90 days | 100+ |
| Releases, last 12 months | 21 (latest 20261014, 2026-10-14) |
| Contributors | 78 (top contributor: 89% of commits) |
| Issues closed, last 90 days | 3+ (typically closed in 1 day) |
| Pull requests merged, last 90 days | 89 (typically merged in 0 days) |
| Project age | 2 years |
Checked on 2026-10-18 with the GitHub API.
Overview
BirdNET-Go is a self-hosted, real-time soundscape analyser built around BirdNET, the bird-audio model developed by the Cornell Lab of Ornithology and Chemnitz University of Technology. It listens continuously to soundcard input or network audio streams, identifies wildlife, and presents detections in a web interface. It runs on Linux, Windows, and macOS, including Raspberry Pi systems.
The project is for people who want to monitor wildlife audio locally rather than send recordings to a hosted analysis service. BirdNET is embedded by default; optional models include Google Perch v2 and regional BattyBirdNET classifiers. Multiple models and audio sources can run in parallel, with alerting and integrations for sending detections elsewhere.
Key Features
- Continuous audio analysis from a soundcard or RTSP/RTSPS streams, with support for multiple sources.
- Embedded BirdNET model, plus installable Google Perch v2, BattyBirdNET, and BirdNET Geomodel classifiers.
- Cross-model consensus, configurable confidence thresholds, and filtering tools to help review detections.
- Live spectrograms, detection heatmaps, and an installable web app.
- Alert rules that can send notifications through services such as Discord, Telegram, ntfy, MQTT, and webhooks.
- SQLite or MySQL storage, with backups and database diagnostics.
- Optional integrations including BirdWeather, Home Assistant discovery, and Prometheus metrics.
Use Cases
- Birders can run an always-on listening station at home and browse detections from a web dashboard.
- Wildlife researchers or conservation groups can monitor audio from multiple network microphones and compare classifier results.
- Bat monitoring requires an ultrasonic-capable recording setup; BattyBirdNET is available for Linux with regional models.
- Raspberry Pi owners can build a local wildlife monitoring system without relying on a hosted inference service.
What you need
Detected in the repository
- Go 1.27.2 or newer (from go.mod)
- A Dockerfile, so it can run in a container
- Automated checks on GitHub Actions
Getting Started
On Debian, Ubuntu, or Raspberry Pi OS:
curl -fsSL https://github.com/tphakala/birdnet-go/raw/main/install.sh -o install.sh
bash ./install.sh
For Docker, other platforms, hardware guidance, and configuration, see the installation guide and the README.
License in Plain Words
No standard license was detected. Without a license, the default copyright rules apply: you may read the code, but not reuse it. Check the repository or ask the authors.
Considerations
- The project is active, with regular commits and releases, but most code contributions come from one person despite a larger contributor pool. The open issue backlog is substantial, although the reported median time to close issues is short.
- Running continuously requires a suitable microphone or network audio stream and a host that can stay online. Bat detection additionally calls for an ultrasonic-capable device; optional ONNX models require ONNX Runtime.
- The default storage is SQLite, with MySQL also supported. This is a self-hosted application, so operators need to manage the host and its data.
- The README states the project is licensed under CC BY-NC-SA 4.0. Review its noncommercial and share-alike terms before adopting or redistributing it.
- Repository metadata does not report a test suite. Teams evaluating changes or integrating the software may want to assess their own verification needs.
Found this useful?
Share it with someone who would like birdnet-go.