Genkit
Type: full-code · Vendor: Google (Firebase) · Language: TypeScript, Go, Python · License: Apache-2.0 · Status: active · Status in practice: emerging
Provider-neutral framework for building AI-powered apps with unified APIs, tool calling and agentic workflows.
Description. Google/Firebase full-stack AI framework with unified APIs across providers (Google, OpenAI, Anthropic, Ollama), structured output, RAG, multimodal support and agentic tool-calling flows. Production-ready in JavaScript/TypeScript and Go, with Python in beta; built and used in production by Google.
Agent loop shape. Developers compose named flows that call models with tools and structured-output schemas; flows can chain steps and run agentic tool-calling loops over a unified provider abstraction.
Primary use cases
- building production AI features with one API across multiple model providers
- tool-calling flows and lightweight agentic workflows in JS/Go/Python
- RAG and structured-output pipelines
Key concepts
Patterns this full-code implements —
- ★★Tool Use
Use streamlined APIs to build AI features with structured output, agentic tool calling, context-aware generation, multi-modal input/output, and more.
- ★★Structured Output
Type-safe, structured data generation
- ★★Multi-Model Routing
Use a unified interface to integrate with hundreds of models from providers like Google, OpenAI, Anthropic, Ollama, and more.
- ★★Agentic RAG
AI-powered data retrieval (RAG)
Neighbourhood
Click any neighbour to follow the lineage. Scroll to zoom, drag to pan.
Instantiates
Alternatives & relatives
Listed as alternative by (2)
References
Provenance
- Last analyzed:
- Last updated:
- Verification status: partial