Genkit is an open-source framework for building full-stack, AI-powered applications, created and used in production by Google’s Firebase team. It gives developers a unified interface for integrating models from providers such as Google, OpenAI, Anthropic and Ollama, with SDKs for JavaScript/TypeScript and Go in production shape, Python in beta and Dart in preview. The framework has about 6,500 stars on GitHub and is actively maintained through 2026, covering everything from chatbots and agents to RAG pipelines and multimodal apps.
Building AI features usually means gluing together provider SDKs, prompt management, retrieval, tool calling and observability by hand. Genkit packages those pieces into one framework: define flows as type-safe, testable functions; manage prompts as code; plug in embedders and vector databases for retrieval-augmented generation; and expose tools and agents that models can call. Because it comes from the Firebase team, it is designed to deploy into real production stacks, and it includes developer tooling for running, inspecting and debugging flows locally. A plugin ecosystem covers model providers, vector stores and more, so teams can swap providers without rewriting their application logic, and structured output support helps keep model responses machine-readable.
Genkit is completely free and open source under the Apache-2.0 license. You only pay for the model APIs and hosting infrastructure you choose to plug into it.
Genkit is for application developers and teams who want a production-grade, provider-neutral way to build AI features — chatbots, agents, automation and multimodal experiences — especially those already working in the Firebase and Google Cloud ecosystem.