← All examples

Google Gemini Agent

Agent using the Google Generative AI SDK. Gemini models with function calling and streaming.

agentgooglegemini
Deploy this example

Agent using the Google Generative AI SDK. Gemini models with function calling and streaming — direct SDK usage for full control.

What's included

  • Google AI SDK — official @google/generative-ai client
  • Gemini models — Gemini 1.5 Pro, Gemini 1.5 Flash, and more
  • Function calling — define tools and let Gemini invoke them
  • Streaming — real-time token streaming via SSE
  • Direct access — no abstraction layer, full SDK control

When to use this

Pick this example when you want to:

  • Use the Google Generative AI SDK directly
  • Build agents with Gemini models
  • Leverage Google's multimodal and long-context capabilities

Project structure

├── src/
│   ├── index.ts                # Entry point — serve({ agents })
│   └── agents/
│       └── gemini-agent.ts     # Google AI SDK agent
├── package.json
├── tsconfig.json
└── reminix.config.ts

Quick start

Deploy the example and invoke the agent via the Reminix API. The Google AI SDK handles chat completions, function calling, and streaming — you get a production REST endpoint with direct Gemini access.