​
Install AgentMark with an adapter

Install with npm:
npm
npm install @agentmark/agentmark-core @agentmark/vercel-ai-v4-adapter
or yarn:
npm
yarn add @agentmark/agentmark-core @agentmark/vercel-ai-v4-adapter

​
Create your first Prompt

example.prompt.mdx
---
name: example
text_config:
  model_name: gpt-4o-mini
---

<User>Hello World</User>

​
Run your Prompt

Run .prompt.mdx files directly within your VSCode editor. Download the VSCode Extension

​
File System

Run AgentMark directly in your Node.js environment using vercel ai sdk. Below is a sample implementation:
node
import { FileLoader } from "@agentmark/agentmark-core";
import { generateText } from "ai";
import {
  VercelAIModelRegistry,
  createAgentMarkClient
} from "@agentmark/vercel-ai-v4-adapter";
// use any ai-sdk model provider
import { openai } from "@ai-sdk/openai";

const modelRegistry = new VercelAIModelRegistry();
// register models you want to use
modelRegistry.registerModels(['gpt-4o'], (name: string) => {
  return openai(name);
});

const loader = new FileLoader('./path/to/prompts');

const agentmark = createAgentMarkClient({
  loader,
  modelRegistry,
});

const run = async () => {
  const examplePrompt = await agentmark.loadTextPrompt('<example>.prompt.mdx');
  const props = { name: "Emily" };
  const vercelInput = await examplePrompt.format({props});
  const result = await generateText(vercelInput);
  console.log(result);
}
run();

​
AgentMark Cloud

Collaborate with your team on prompts and agents with AgentMark’s Cloud platform.
node
import { generateText } from "ai";
import {
  VercelAIModelRegistry,
  createAgentMarkClient
} from "@agentmark/vercel-ai-v4-adapter";
import { AgentMarkSDK } from "@agentmark/sdk";
// use any ai-sdk model provider
import { openai } from "@ai-sdk/openai";

const modelRegistry = new VercelAIModelRegistry();
// register models you want to use
modelRegistry.registerModels(['gpt-4o'], (name: string) => {
  return openai(name);
});

const sdk = new AgentmarkClient({
  apiKey: process.env.AGENTMARK_API_KEY!,
  appId: process.env.AGENTMARK_APP_ID!
});

const agentmark = createAgentMarkClient({
  loader: sdk.getFileLoader(),
  modelRegistry,
});

const run = async () => {
  const examplePrompt = await agentmark.loadTextPrompt("<example>.prompt.mdx");
  const props = { name: "Emily" };
  const vercelInput = await examplePrompt.format({props});
  const result = await generateText(vercelInput);
  console.log(result);
}
run();

​
Have Questions?

We’re here to help! Choose the best way to reach us: