google-ai-edge/mediapipe-samples resource

Health v2 · maintenance only

Adoption not part of the score

2809 stars · 767 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

learning-resource · maturity active

machine-learning computer-vision speech-recognition llm-inference sdk machine-learning computer-vision artificial-intelligence mobile-development web-development tutorials python cross-platform mediapipe on-device-ml sample-code jupyter-notebooks google-ai-edge on-device-inference android ios web-server gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="google-ai-edge/mediapipe-samples")