genkit-ai/genkit

Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

What it solves

Genkit is an open-source framework designed to simplify the process of building, deploying, and monitoring full-stack AI-powered applications. It removes the complexity of integrating various AI models and managing the server-side logic required for production-ready AI features like chatbots and recommendation systems.

How it works

Genkit provides a unified interface and SDKs across multiple languages (JavaScript/TypeScript, Go, Python, and Dart) that abstract away the specific APIs of different model providers. This allows developers to integrate models from providers like Google, OpenAI, Anthropic, and Ollama using a consistent set of APIs for multimodal content, structured outputs, and tool calling.

Who it’s for

It is built for full-stack developers who want to build AI applications across different platforms (Web, iOS, Android) and deploy them to any environment that supports their chosen language, including Firebase and Google Cloud Run.

Highlights

  • Broad Model Support: Unified interface for hundreds of models from various providers.
  • Developer Tools: Includes a local CLI and Developer UI for testing prompts, debugging with execution traces, and comparing model outputs.
  • Production Monitoring: Dedicated dashboards to track performance, latency, and error rates in real-world usage.
  • Cross-Language SDKs: Production-ready support for JS/TS and Go, with Beta/Preview support for Python and Dart.
  • AI Workflow Capabilities: Built-in support for RAG (Retrieval Augmented Generation), prompt templating, and agentic tool calling.

Related

  • Project
    google/adk-java

    Google’s ADK‑Java is a Maven‑distributed Java library for building, testing, and deploying LLM‑powered AI agents. It offers a code‑first builder API, a rich tool ecosystem (including Google Search), multi‑agent composition, a web‑based development UI, and integration with Google’s A2A protocol for remote agent communication.

  • Project
    dabit3/react-native-ai

    A full-stack framework for building cross-platform mobile AI apps with built-in support for real-time LLM streaming and image generation.

  • Project
    google/adk-go

    Google's Agent Development Kit for Go is an open-source, code-first framework for building, evaluating, and deploying modular AI agents. It applies software engineering practices—such as versioning and testability—to agent development, and is model-agnostic while optimized for Gemini.

  • Project
    microsoft/teams-sdk

    A comprehensive development framework for building AI-powered agents and applications integrated into Microsoft Teams.

  • Project
    CopilotKit/CopilotKit

    CopilotKit is an SDK that connects AI agents to user interfaces, enabling developers to build agent-native applications with generative UI, shared state, and multi-platform support.