@reminix/anthropic

Reminix Runtime adapter for the Anthropic API. Serve Claude models as a REST API.

Ready to go live? Deploy to Reminix Cloud for zero-config hosting, or self-host on your own infrastructure.

Installation

npm install @reminix/anthropic @anthropic-ai/sdk

This will also install @reminix/runtime as a dependency.

Quick Start

import Anthropic from '@anthropic-ai/sdk';
import { serveAgent } from '@reminix/anthropic';

const client = new Anthropic();
serveAgent(client, { name: 'my-claude', model: 'claude-sonnet-4-20250514', port: 8080 });

For more flexibility (e.g., serving multiple agents), use wrapAgent and serve separately:

import Anthropic from '@anthropic-ai/sdk';
import { wrapAgent } from '@reminix/anthropic';
import { serve } from '@reminix/runtime';

const client = new Anthropic();
const agent = wrapAgent(client, { name: 'my-claude', model: 'claude-sonnet-4-20250514' });
serve({ agents: [agent], port: 8080 });

Your agent is now available at:

• POST /agents/my-claude/invoke - Execute the agent

API Reference

serveAgent(client, options)

Wrap an Anthropic client and serve it immediately. Combines wrapAgent and serve for single-agent setups.

| Parameter | Type | Default | Description | |-----------|------|---------|-------------| | client | Anthropic | required | An Anthropic client | | options.name | string | "anthropic-agent" | Name for the agent (used in URL path) | | options.model | string | "claude-sonnet-4-20250514" | Model to use | | options.maxTokens | number | 4096 | Maximum tokens in response | | options.port | number | 8080 | Port to serve on | | options.hostname | string | "0.0.0.0" | Hostname to bind to |

wrapAgent(client, options)

Wrap an Anthropic client for use with Reminix Runtime. Use this with serve from @reminix/runtime for multi-agent setups.

| Parameter | Type | Default | Description | |-----------|------|---------|-------------| | client | Anthropic | required | An Anthropic client | | options.name | string | "anthropic-agent" | Name for the agent (used in URL path) | | options.model | string | "claude-sonnet-4-20250514" | Model to use | | options.maxTokens | number | 4096 | Maximum tokens in response |

Returns: AnthropicAgentAdapter - A Reminix adapter instance

System Messages

The adapter automatically handles Anthropic's system message format. System messages in your request are extracted and passed as the system parameter to the API.

// This works automatically:
const request = {
  messages: [
    { role: 'system', content: 'You are a helpful assistant' },
    { role: 'user', content: 'Hello!' },
  ],
};

Endpoint Input/Output Formats

POST /agents/{name}/invoke

Execute the agent with a prompt or messages.

Request with prompt:

{
  "prompt": "Summarize this text: ..."
}

Request with messages:

{
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ]
}

Response:

{
  "output": "Hello! How can I help you today?"
}

Streaming

For streaming responses, set stream: true in the request:

{
  "prompt": "Tell me a story",
  "stream": true
}

The response will be sent as Server-Sent Events (SSE).

Runtime Documentation

For information about the server, endpoints, request/response formats, and more, see the @reminix/runtime package.

Deployment

Ready to go live?

• Deploy to Reminix Cloud - Zero-config cloud hosting
• Self-host - Run on your own infrastructure

Links

• GitHub Repository
• Anthropic Documentation

License

Apache-2.0