Genkit

What is Genkit about?

Genkit provides a code‑centric framework for creating, testing, and deploying AI features such as text or image generation, structured output, tool‑calling agents, RAG, and multimodal workflows. It abstracts model‑provider differences behind a single interface and offers client SDKs for JavaScript/TypeScript, Go, and Python.

How to use Genkit?

1. Choose a language – install the SDK for JavaScript/TypeScript (stable), Go (beta) or Python (alpha).
2. Add a model provider – install the plugin for Google Gemini, OpenAI, Anthropic, Ollama, etc., and supply the required API key.
3. Initialize the framework – import genkit and the provider, then call genkit({ plugins: [...] }).
4. Write AI features – use ai.generate, flow, prompt, or the chat helpers to create functions.
5. Test locally – run npx genkit-cli start -- <your‑command> to launch the CLI with the interactive Developer UI.
6. Deploy – ship the code to Cloud Functions for Firebase, Cloud Run, or any compatible environment.

Key features of Genkit

• Broad model support – unified API for hundreds of models across multiple providers.
• Structured output & tool calling – type‑safe schemas and agentic workflows.
• Multimodal I/O – handle text, images, and other media in a single flow.
• RAG & context‑aware generation – built‑in retrieval utilities.
• Cross‑language SDKs – consistent experience in JS/TS, Go, and Python.
• Developer UI & CLI – prompt playground, execution tracing, evaluation dashboards.
• Production observability – metrics, latency, error tracking, and a monitoring dashboard.
• Easy deployment – works with Firebase, Cloud Run, or any Node/Go/Python runtime.

Use cases of Genkit

• Chatbots & virtual assistants – build conversational agents with tool calling and memory.
• Content generation – generate blog posts, code snippets, or images on demand.
• Recommendation systems – combine LLM reasoning with vector search for personalized results.
• Enterprise automation – automate workflows like ticket triage, document summarization, or data extraction.
• Prototyping AI products – rapidly iterate on prompts and models before scaling to production.

FAQ from the Genkit

Q: Which languages are production‑ready? A: JavaScript/TypeScript is stable; Go is beta and may change; Python is currently alpha.

Q: How do I add a new model provider? A: Install the corresponding plugin package (e.g., @genkit-ai/googleai), import it, and include it in the plugins array when initializing Genkit.

Q: Do I need Google Cloud to run Genkit? A: No. Genkit can run on any environment that supports the chosen language, including local machines, third‑party cloud platforms, or on‑prem servers.

Q: How is observability handled? A: The framework emits detailed execution traces and aggregates metrics that are viewable in the built‑in dashboard or can be exported to external monitoring systems.

Q: Can I use Genkit for edge or mobile apps? A: Yes. Client‑side helpers are provided for React, Next.js, iOS, and Android, allowing you to call Genkit‑hosted functions from the edge or mobile devices.

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.