Developing Genkit Dart

1---2name: developing-genkit-dart3description: Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.4metadata:5  genkit-managed: true6---7 8# Genkit Dart9 10Genkit Dart is an AI SDK for Dart that provides a unified interface for code generation, structured outputs, tools, flows, and AI agents.11 12## Core Features and Usage13If you need help with initializing Genkit (`Genkit()`), Generation (`ai.generate`), Tooling (`ai.defineTool`), Flows (`ai.defineFlow`), Embeddings (`ai.embedMany`), streaming, or calling remote flow endpoints, please load the core framework reference: 14[references/genkit.md](references/genkit.md)15 16## Genkit CLI (recommended)17 18The Genkit CLI provides a local development UI for running Flow, tracing executions, playing with models, and evaluating outputs.19 20check if the user has it installed: `genkit --version`21 22**Installation:**23```bash24curl -sL cli.genkit.dev | bash # Native CLI25# OR26npm install -g genkit-cli # Via npm27```28 29**Usage:**30Wrap your run command with `genkit start` to attach the Genkit developer UI and tracing:31```bash32genkit start -- dart run main.dart33```34 35## Plugin Ecosystem36Genkit relies on a large suite of plugins to perform generative AI actions, interface with external LLMs, or host web servers.37 38When asked to use any given plugin, always verify usage by referring to its corresponding reference below. You should load the reference when you need to know the specific initialization arguments, tools, models, and usage patterns for the plugin:39 40| Plugin Name | Reference Link | Description |41| ---- | ---- | ---- |42| `genkit_google_genai` | [references/genkit_google_genai.md](references/genkit_google_genai.md) | Load for Google Gemini plugin interface usage. |43| `genkit_anthropic` | [references/genkit_anthropic.md](references/genkit_anthropic.md) | Load for Anthropic plugin interface for Claude models. |44| `genkit_openai` | [references/genkit_openai.md](references/genkit_openai.md) | Load for OpenAI plugin interface for GPT models, Groq, and custom compatible endpoints. |45| `genkit_middleware` | [references/genkit_middleware.md](references/genkit_middleware.md) | Load for Tooling for specific agentic behavior: `filesystem`, `skills`, and `toolApproval` interrupts. |46| `genkit_mcp` | [references/genkit_mcp.md](references/genkit_mcp.md) | Load for Model Context Protocol integration (Server, Host, and Client capabilities). |47| `genkit_chrome` | [references/genkit_chrome.md](references/genkit_chrome.md) | Load for Running Gemini Nano locally inside the Chrome browser using the Prompt API. |48| `genkit_shelf` | [references/genkit_shelf.md](references/genkit_shelf.md) | Load for Integrating Genkit Flow actions over HTTP using Dart Shelf. |49| `genkit_firebase_ai` | [references/genkit_firebase_ai.md](references/genkit_firebase_ai.md) | Load for Firebase AI plugin interface (Gemini API via Vertex AI). |50 51## External Dependencies52Whenever you define schemas mapping inside of Tools, Flows, and Prompts, you must use the [schemantic](https://pub.dev/packages/schemantic) library. 53To learn how to use schemantic, ensure you read [references/schemantic.md](references/schemantic.md) for how to implement type safe generated Dart code. This is particularly relevant when you encounter symbols like `@Schema()`, `SchemanticType`, or classes with the `$` prefix. Genkit Dart uses schemantic for all of its data models so it's a CRITICAL skill to understand for using Genkit Dart.54 55## Best Practices56- Always check that code cleanly compiles using `dart analyze` before generating the final response.57- Always use the Genkit CLI for local development and debugging.