Build, test, and deploy powerful AI features
Use an intuitive, open source framework, local developer tooling, and integrated cloud services to build and ship sophisticated AI features with your mobile and web apps.
Easily put together the AI components you need
Genkit reduces the complexity of integrating AI components by giving you plugins, templates, and simple abstractions so you can use AI models with your own custom logic and data to build AI features optimized for your business.
Confidently ship with Firebase and Google Cloud
Deploy serverless AI features using Cloud Functions for Firebase or Cloud Run with a single command. Securely serve and scale your AI features with Genkit's robust integrations for tracing, logging, monitoring, authentication, and app attestation. Use the Cloud Functions for Firebase client SDKs to easily call your AI logic from your mobile or web app clients.
Debug and iterate on your AI feature with a rich local development experience
To assist you with the unique debugging challenges that come with AI features, Genkit comes with a locally-running, browser-based UI. You can use it to quickly experiment with AI components, locally execute your end-to-end workflow to test outcomes, and view complete traces for full observability and efficient debugging.
Make use of pre-built components and integrations for models, vector stores, tools, evaluators, observability, and more through Genkit's open ecosystem of plugins built by Google and the community.
Generate strongly-typed data with Genkit to help you analyze unstructured text, generate creative content, select tasks, and send results back to your app as structured type-safe objects.
Genkit provides a common format for content that supports combinations of text, data, and other media. This lets you use Genkit for models that perform any generative task (such as image generation), not just LLMs.
Documentation
Learn how to get started with Firebase Genkit by reviewing our technical documentation
Pricing
Firebase Genkit is a framework without its own cost. Pricing depends on which models and services are used through and with Firebase Genkit.