genkit

Type-safe AI workflows with flows, agents, RAG, and multi-model support across TypeScript, Go, and Python. Flows are the core primitive: type-safe, observable, deployable AI functions. Manage prompts as versioned .prompt files: The Developer UI runs at and provides: - Supports Gemini, OpenAI, Anthropic, Ollama, and Vertex AI with pluggable model providers; deploy to Firebase Cloud Functions or Cloud Run - Define type-safe flows with Zod schemas for inputs/outputs; includes streaming, tool calling, and agentic loops with auto-execution - Built-in RAG with vector database integrations (Pinecone, pgvector, Firestore, Chroma, LanceDB) and retrieval-augmented generation - Developer UI at localhost:4000 provides flow runner, trace inspector, prompt playground, and model comparison tools - Manage prompts as versioned .prompt files with Dotprompt; coordinate multi-agent systems by composing specialized flows - AI workflow orchestration : Building multi-step AI pipelines with type-safe inputs/outputs - Flow-based APIs : Wrapping LLM calls into deployable HTTP endpoints - Tool calling / agents : Equipping models with custom tools and implementing agentic loops - RAG pipelines : Retrieval-augmented generation with vector databases (Pinecone, pgvector, Firestore, Chroma, etc.) - Multi-agent systems : Coordinating multiple specialized AI agents - Streaming responses : Real-time...