TypeScript social media agent (Mastra) template

An AI agent for social media research, built on a TypeScript-native framework.

Create it locally

$scrapely create my-actor --template ts-mastraai

Main file

.TS

src/main.ts

import { Actor, log } from 'scrapely';

import { createWebResearchAgent } from './agents.js';

// this is ESM project, and as such, it requires you to specify extensions in your relative imports
// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
// note that we need to use `.js` even when inside TS files
// import { router } from './routes.js';

// Actor input schema
interface Input {
    query: string;
    modelName: string;
}

// The init() call configures the Actor to correctly work with the platform-provided environment - mainly the storage infrastructure. It is necessary that every Actor performs an init() call.
await Actor.init();

/**
 * Actor code
 */

// Handle input
const {
    // The query default value is provided only for template testing purposes.
    // You can remove it.
    query,
    modelName,
} = (await Actor.getInput()) as Input;
if (!query) {
    throw new Error('An agent query is required.');
}

// Create the web research agent with tools
const agent = createWebResearchAgent(modelName);

log.info(`Querying the agent with the following query: ${query}`);

// Query the agent and get the response
const response = await agent.generate([{ role: 'user', content: query }]);

log.info(`Agent response: ${response.text}`);

// Charge for the task completion
await Actor.charge({ eventName: 'task-completed' });

// Push results into the dataset
await Actor.pushData({
    query,
    response: response.text,
});

// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
await Actor.exit();

TypeScript web research agent (Mastra)

A Mastra agent that researches websites with a page-scraping tool, built on a TypeScript-native framework.

Included features

Scrapely SDK — Actor lifecycle, input, storage and proxies
Mastra — TypeScript agent framework
Scrapely LLM gateway — call OpenRouter models with the run token; usage is billed to your Scrapely account, no provider API key needed
Input schema — define and validate the Actor's input (.actor/input_schema.json)
Dataset schema — structured results with a preview view (.actor/dataset_schema.json)

Getting started locally

npm install
npm run start      # run the Actor
npm run build      # compile to dist/

LLM calls go to SCRAPELY_LLM_BASE_URL (set automatically on the platform) with the run's SCRAPELY_TOKEN, so the agent works inside a Scrapely run without any provider API key.

Deploying to Scrapely

Create an Actor from this template in the Scrapely Console (Develop new → template → Git). Scrapely creates a repository in your account, pushes this code, and builds the Actor. Every push to your repository triggers a new build.