TypeScript Client Setup
The AgentMark client is configured in agentmark.client.ts. It connects your prompts to AI models, tools, evaluations, and prompt loading. This file is auto-generated by npm create agentmark@latest — you can customize it after setup.
Choose Your Adapter
AI SDK (Vercel)
Claude Agent SDK
Mastra
npm install @agentmark-ai/ai-sdk-v5-adapter @agentmark-ai/loader-api @ai-sdk/openai
import {
createAgentMarkClient,
VercelAIModelRegistry,
} from "@agentmark-ai/ai-sdk-v5-adapter";
import { ApiLoader } from "@agentmark-ai/loader-api";
import { openai } from "@ai-sdk/openai";
const loader =
process.env.NODE_ENV === "development"
? ApiLoader.local({
baseUrl: process.env.AGENTMARK_BASE_URL || "http://localhost:9418",
})
: ApiLoader.cloud({
apiKey: process.env.AGENTMARK_API_KEY!,
appId: process.env.AGENTMARK_APP_ID!,
});
const modelRegistry = new VercelAIModelRegistry()
.registerModels(["gpt-4o", "gpt-4o-mini"], (name) => openai(name))
.registerModels(["dall-e-3"], (name) => openai.image(name))
.registerModels(["tts-1-hd"], (name) => openai.speech(name));
export const client = createAgentMarkClient({
loader,
modelRegistry,
});
generateText(), generateObject(), streamText(), streamObject().npm install @agentmark-ai/claude-agent-sdk-v0-adapter @agentmark-ai/loader-api
import {
createAgentMarkClient,
ClaudeAgentModelRegistry,
} from "@agentmark-ai/claude-agent-sdk-v0-adapter";
import { ApiLoader } from "@agentmark-ai/loader-api";
const loader =
process.env.NODE_ENV === "development"
? ApiLoader.local({
baseUrl: process.env.AGENTMARK_BASE_URL || "http://localhost:9418",
})
: ApiLoader.cloud({
apiKey: process.env.AGENTMARK_API_KEY!,
appId: process.env.AGENTMARK_APP_ID!,
});
const modelRegistry = ClaudeAgentModelRegistry.createDefault();
export const client = createAgentMarkClient({
loader,
modelRegistry,
adapterOptions: {
permissionMode: "bypassPermissions",
maxTurns: 20,
},
});
| Option | Description |
|---|
permissionMode | 'default', 'acceptEdits', 'bypassPermissions', or 'plan' |
maxTurns | Maximum number of agent turns |
maxBudgetUsd | Spending limit per run |
cwd | Working directory for the agent |
allowedTools | Whitelist of tool names |
disallowedTools | Blacklist of tool names |
npm install @agentmark-ai/mastra-v0-adapter @agentmark-ai/loader-api @ai-sdk/openai
import {
createAgentMarkClient,
MastraModelRegistry,
} from "@agentmark-ai/mastra-v0-adapter";
import { ApiLoader } from "@agentmark-ai/loader-api";
import { openai } from "@ai-sdk/openai";
const loader =
process.env.NODE_ENV === "development"
? ApiLoader.local({
baseUrl: process.env.AGENTMARK_BASE_URL || "http://localhost:9418",
})
: ApiLoader.cloud({
apiKey: process.env.AGENTMARK_API_KEY!,
appId: process.env.AGENTMARK_APP_ID!,
});
const modelRegistry = new MastraModelRegistry()
.registerModels(["gpt-4o", "gpt-4o-mini"], (name) => openai(name));
export const client = createAgentMarkClient({
loader,
modelRegistry,
});
Model Registry
Register models by name, mapping them to provider-specific constructors:
const modelRegistry = new VercelAIModelRegistry()
// Text models
.registerModels(["gpt-4o", "gpt-4o-mini"], (name) => openai(name))
// Image models
.registerModels(["dall-e-3"], (name) => openai.image(name))
// Speech models
.registerModels(["tts-1-hd"], (name) => openai.speech(name));
model_name in your prompt frontmatter.
Prompt Loading
The loader determines how prompts are fetched at runtime:
// Local — loads from dev server (development)
const loader = ApiLoader.local({
baseUrl: "http://localhost:9418",
});
// Cloud — loads from AgentMark CDN (production)
const loader = ApiLoader.cloud({
apiKey: process.env.AGENTMARK_API_KEY!,
appId: process.env.AGENTMARK_APP_ID!,
});
loadTextPrompt() within the TTL return the cached version without a network request.
Adding Tools
Pass tools to the client via the tools option:
import { tool } from "ai";
import { z } from "zod";
export const client = createAgentMarkClient({
loader,
modelRegistry,
tools: {
calculate: tool({
description: "Performs arithmetic calculations",
parameters: z.object({
expression: z.string(),
}),
execute: async ({ expression }) => {
return { result: Function(`"use strict"; return (${expression})`)() };
},
}),
},
});
Full Reference
For all configuration options including evals, MCP servers, and advanced loader options, see Client Config.
Have Questions?
We’re here to help! Choose the best way to reach us:
