An AI agent that tells jokes, built with PydanticAI. A starting point for any AI agent.
Create it locally
$scrapely create my-actor --template python-pydanticai
Main file
.PY
my_actor/main.py"""Module defines the main entry point for the Scrapely Actor.
Feel free to modify this file to suit your specific needs.
To build Scrapely Actors, utilize the Scrapely SDK toolkit, read more at the official documentation:
"""
from __future__ import annotations
from scrapely import Actor
from .agents import Deps, get_joker_agent
async def main() -> None:
"""Define a main entry point for the Scrapely Actor."""
async with Actor:
# Charge for Actor start
await Actor.charge('actor-start')
Actor.log.info('Starting joke generation agent.')
# Process inputs
actor_input = await Actor.get_input()
if not (joke_topic := actor_input.get('jokeTopic')):
await Actor.fail(status_message='Missing "jokeTopic" attribute in input!')
model_name = actor_input.get('modelName', 'deepseek/deepseek-v4-flash')
# Generate joke
agent = get_joker_agent(model_name)
joke = (
await agent.run(user_prompt='Tell me a joke.', deps=Deps(joke_topic=joke_topic, model_name=model_name))
).output
Actor.log.info(f'The AI generated joke about {joke_topic}:\n{joke}')
# Store the joke
dataset = await Actor.open_dataset()
await dataset.push_data({'Topic': joke_topic, 'Joke': joke})
# Charge for task completion
await Actor.charge('task-completed')
Python joke agent (PydanticAI)
An AI agent that tells jokes, built with PydanticAI. A starting point for any AI agent.
Included features
- Scrapely SDK — Actor lifecycle, input, storage and proxies
- PydanticAI — 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
python -m pip install -r requirements.txt
scrapely run # run the Actor locally
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.
