Genkit

What is Genkit about?

Genkit is an open‑source framework that simplifies the creation of full‑stack AI‑powered applications. It abstracts model provider differences, supports structured outputs, tool calling, multimodal content, and RAG, and offers local developer tools and production‑grade observability.

How to use Genkit?

1. Choose a language – install the JavaScript/TypeScript SDK (stable), Go SDK (beta) or Python SDK (alpha).
2. Add a model provider plugin – e.g., @genkit-ai/googleai, @genkit-ai/openai, etc.
3. Initialize the Genkit instance with the desired plugins.
4. Write AI features using the concise generate, flow, prompt, and chat APIs.
5. Test locally with the Genkit CLI (npx genkit-cli start …) and the Developer UI.
6. Deploy to Cloud Functions, Cloud Run, or any compatible environment and monitor via the built‑in dashboard.

import { genkit } from 'genkit';
import { googleAI } from '@genkit-ai/googleai';

const ai = genkit({ plugins: [googleAI()] });

const { text } = await ai.generate({
  model: googleAI.model('gemini-2.0-flash'),
  prompt: 'Why is Firebase awesome?'
});

Key features of Genkit

• Broad model support – Unified API for Google, OpenAI, Anthropic, Ollama, Vertex AI, etc.
• Structured output & type‑safety – Generate JSON‑compatible data directly.
• Agentic tool calling – Build agents that invoke external tools or APIs.
• Multimodal I/O – Handle text, images, and other media in a single flow.
• RAG & context‑aware generation – Retrieve relevant data from vector stores.
• Cross‑language SDKs – Consistent APIs for JavaScript/TypeScript, Go, and Python.
• Developer UI & CLI – Interactive playground, trace inspection, evaluation dashboards.
• Production monitoring – Latency, error rates, token usage visualized in a dedicated dashboard.
• Seamless deployment – Works with Firebase Functions, Cloud Run, or any Node/Go/Python runtime.

Use cases of Genkit

• Building customer‑support chatbots with tool integration.
• Creating recommendation engines that retrieve data from vector databases.
• Developing multimodal content generators (text + image).
• Implementing AI‑augmented workflows in web or mobile apps.
• Rapid prototyping of AI agents for internal tooling or SaaS products.

FAQ from Genkit

Q: Which language should I start with? A: JavaScript/TypeScript is production‑ready; Go and Python are available for early adopters.

Q: Do I need a Google Cloud account? A: No. Genkit works with any supported provider (OpenAI, Anthropic, Ollama, etc.). Google services are optional.

Q: How does monitoring work? A: The framework emits telemetry that the built‑in dashboard aggregates, showing request volume, latency, error rates, and model performance.

Q: Can I run Genkit on my own server? A: Yes. Deploy the generated code to any environment that runs the chosen language runtime.

Q: Is there a way to test prompts without writing code? A: The local Developer UI provides a playground for ad‑hoc prompt testing and flow execution.

Genkit is an open-source framework for building full-stack AI-powered applications, built and used in production by Google's Firebase. It provides SDKs for multiple programming languages with varying levels of stability:

• JavaScript/TypeScript (Stable): Production-ready with full feature support
• Go (Beta): Feature-complete but may have breaking changes
• Python (Alpha): Early development with core functionality

It offers a unified interface for integrating AI models from providers like Google, OpenAI, Anthropic, Ollama, and more. Rapidly build and deploy production-ready chatbots, automations, and recommendation systems using streamlined APIs for multimodal content, structured outputs, tool calling, and agentic workflows.

Get started with just a few lines of code:

import { genkit } from 'genkit';
import { googleAI } from '@genkit-ai/googleai';

const ai = genkit({ plugins: [googleAI()] });

const { text } = await ai.generate({
    model: googleAI.model('gemini-2.0-flash'),
    prompt: 'Why is Firebase awesome?'
});

Explore & build with Genkit

Play with AI sample apps, with visualizations of the Genkit code that powers them, at no cost to you.

Explore Genkit by Example

Key capabilities

How does it work?

Genkit simplifies AI integration with an open-source SDK and unified APIs that work across various model providers and programming languages. It abstracts away complexity so you can focus on delivering great user experiences.

Some key features offered by Genkit include:

• Text and image generation
• Type-safe, structured data generation
• Tool calling
• Prompt templating
• Persisted chat interfaces
• AI workflows
• AI-powered data retrieval (RAG)

Genkit is designed for server-side deployment in multiple language environments, and also provides seamless client-side integration through dedicated helpers and client SDKs.

Implementation path

Get started

• JavaScript/TypeScript quickstart (Stable)
• Go quickstart (Beta)
• Python quickstart (Alpha)

Development tools

Genkit provides a CLI and a local UI to streamline your AI development workflow.

CLI

The Genkit CLI includes commands for running and evaluating your Genkit functions (flows) and collecting telemetry and logs.

• Install: npm install -g genkit-cli
• Run a command, wrapped with telemetry, a interactive developer UI, etc: genkit start -- <command to run your code>

Developer UI

The Genkit developer UI is a local interface for testing, debugging, and iterating on your AI application.

Key features:

• Run: Execute and experiment with Genkit flows, prompts, queries, and more in dedicated playgrounds.
• Inspect: Analyze detailed traces of past executions, including step-by-step breakdowns of complex flows.
• Evaluate: Review the results of evaluations run against your flows, including performance metrics and links to relevant traces.

Try Genkit in Firebase Studio

Want to skip the local setup? Click below to try out Genkit using Firebase Studio, Google's AI-assisted workspace for full-stack app development in the cloud.

Connect with us

• Join us on Discord – Get help, share ideas, and chat with other developers.
• Contribute on GitHub – Report bugs, suggest features, or explore the source code.
• Contribute to Documentation and Samples – Report issues in Genkit's documentation, or contribute to the samples.

Contributing

Contributions to Genkit are welcome and highly appreciated! See our Contribution Guide to get started.

Authors

Genkit is built by Firebase with contributions from the Open Source Community.