Agent built with the Vercel AI SDK. Get streaming responses, tool calling, and structured output with minimal boilerplate — all served as a production REST API.
What's included
- Vercel AI SDK integration — streaming, tool use, and structured generation out of the box
- Streaming responses — real-time token streaming via SSE
- Tool calling — define tools and let the model invoke them
- Structured output — generate JSON and typed responses with minimal code
When to use this
Pick this example when you want to:
- Use the Vercel AI SDK with Reminix for a production-ready agent
- Get streaming and tool use without writing low-level API code
- Build on a popular, well-maintained AI framework
Project structure
├── src/
│ ├── index.ts # Entry point — serve({ agents })
│ └── agents/
│ └── assistant.ts # Vercel AI SDK agent
├── package.json
├── tsconfig.json
└── reminix.config.ts
Quick start
Deploy the example and invoke the agent via the Reminix API. The Vercel AI SDK handles streaming, tool execution, and structured output — you get a production REST endpoint with minimal configuration.