google-ai-edge/mediapipe

Project overview

MediaPipe provides cross-platform libraries and tools for building and deploying on-device machine learning pipelines that process images, video, and text locally on the user's device. It is intended for developers who need to integrate customizable ML features into Android, iOS, Web, Python, or C++ applications without sending input data to external servers.

Project type

Model Runtime · Infrastructure

Deployment

Refer to project documentation

License

Apache-2.0

Best for

• Developers, AI engineers, and researchers who need to integrate on-device machine learning features with a local-only data boundary.
• Projects that require customizing pre-trained models for deployment across Android, iOS, Web, Python, or C++ applications.

Key capabilities

• Cross-platform APIs and libraries for deploying machine learning solutions in applications.
• Tool to customize pre-trained models with custom data for solutions.
• Tool to visualize, evaluate, and benchmark solutions in a browser.
• Low-level component for building efficient on-device ML pipelines using packets, graphs, and calculators.
• Pre-trained, ready-to-run models for use with each solution.

Limitations and risks

• Support for certain MediaPipe Legacy Solutions ended as of March 1, 2023, which may affect older integrations.
• The APIs send metrics about performance and utilization to Google, which requires obtaining user consent.
• Integrating the libraries and processing on-device inference requires writing code and setting up the development environment.

Getting started

• The setup process requires setting up a development environment and integrating libraries via code. Initial success requires setting up the environment for Python, Web, or Android, integrating MediaPipe Tasks APIs and libraries, and processing on-device inference.

Evidence and sources

• README: Delight your customers with innovative machine learning features.
• README: MediaPipe Solutions provides a suite of libraries and tools for you to quickly apply artificial intelligence (AI) and machine learning (ML) techniques in your applications.
• README: MediaPipe Framework is the low-level component used to build efficient on-device machine learning pipelines, similar to the premade MediaPipe Solutions.
• README: When you use MediaPipe Tasks, processing of the input data (e.g. images, video, text) takes place on device, and MediaPipe does not send that input data to Google servers. As a re…
• Release: MediaPipe v0.10.35

Reviewed at: 2026-07-17T22:11:25Z