# DT42/BerryNet

Deep learning gateway on Raspberry Pi and other edge devices

Repository: https://github.com/DT42/BerryNet
Canonical: https://ross.abutalabs.com/products/berrynet
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: raspberry-pi, deep-learning, tensorflow, iot, mqtt, aiot, edge-devices, edge-ai, openvino, tensorrt, edge-computing
Last push: 2023-02-16T03:10:29+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3415, "days_push": 1294, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1610, forks 224 (observed 2026-08-28T04:05:10.914301+00:00)

## What it is
BerryNet is a deep learning gateway that turns edge devices like Raspberry Pi into intelligent, offline AI hubs for analyzing camera images and video frames. It uses MQTT to connect AI engines (classification and object detection) with dashboards and notifications, and supports building distributed AIoT networks across multiple devices.

## Use cases
- run object detection on a raspberry pi camera feed without internet
- build an offline security camera that alerts when a person or animal appears
- classify images locally on an edge device
- create a distributed AIoT network of smart cameras
- analyze IP camera frames with TinyYOLO or MobileNet SSD
- monitor a meeting room and get notified on events

## When to choose
- you need deep learning inference fully offline on low-power edge hardware
- you want an MQTT-based pipeline connecting cameras, AI engines, and dashboards
- you want to link multiple edge devices into a distributed AIoT setup

## When to avoid
- you need cloud-scale GPU inference or training
- you need a fully managed or actively developed product with frequent updates
- you need models beyond the supported classification/detection engines without custom integration

## Facets
- artifact type: framework
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, message-queue, image-processing, streaming
- domain: artificial-intelligence, iot, computer-vision, embedded-systems
- platform: python, embedded
- tags: edge-ai, raspberry-pi, aiot, mqtt, object-detection, image-classification, openvino, tensorrt, offline-inference, edge-computing, linux, nodejs, docker

## Member repositories
- DT42/BerryNet (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:10.914301+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 2026-08-30T03:51:13.053634+00:00, confidence not recorded.
  - readme: https://github.com/DT42/BerryNet (fetched 2026-08-28T04:05:10.914301+00:00, sha 6115c6ce6115)
  - registry_pypi: https://pypi.org/pypi/berrynet/json (fetched 2026-08-29T11:23:12.627111+00:00, sha 94c1011fb3bb)
- Data as of 2026-08-30T08:39:29.467469+00:00.