# google-ai-edge/mediapipe-samples

Repository: https://github.com/google-ai-edge/mediapipe-samples
Canonical: https://ross.abutalabs.com/products/mediapipe-samples
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2026-08-18T01:43:45+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 40, longevity 100
- inputs: {"age_days": 1412, "days_push": 16, "days_rel": 490, "gap_med": 5.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2809, forks 767 (observed 2026-08-28T04:07:23.607241+00:00)

## What it is
Official collection of sample code and tutorials for Google's MediaPipe on-device machine learning platform. It demonstrates how to build cross-platform ML apps using MediaPipe Tasks for vision, audio, text, and LLM inference.

## Use cases
- run on-device image classification in an android app
- detect objects in real time with mediapipe on ios
- build a web demo for face landmark detection
- run an llm locally on mobile with mediapipe
- learn how to use mediapipe tasks api with python notebooks
- deploy cross-platform ml pipelines without a server

## When to choose
- you want official, maintained example code for MediaPipe Tasks
- you are learning on-device ML deployment across android, ios, web, and python
- you need reference implementations for vision, audio, or text solutions

## When to avoid
- you need a production library itself rather than samples - use the MediaPipe framework repos
- you want to contribute complex custom demos, which this repo rejects
- you need server-side or cloud ML training rather than on-device inference

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, computer-vision, speech-recognition, llm-inference, sdk
- domain: machine-learning, computer-vision, artificial-intelligence, mobile-development, web-development, tutorials
- platform: python, cross-platform
- tags: mediapipe, on-device-ml, sample-code, jupyter-notebooks, google-ai-edge, on-device-inference, android, ios, web-server, gpu

## Member repositories
- google-ai-edge/mediapipe-samples (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:23.607241+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 2026-08-30T08:14:24.937486+00:00, confidence not recorded.
  - readme: https://github.com/google-ai-edge/mediapipe-samples (fetched 2026-08-28T04:07:23.607241+00:00, sha 0ef43f9fe236)
- Data as of 2026-08-30T08:39:29.467469+00:00.