Pydantic Docs

Pydantic is the end-to-end AI Engineering stack. Validate untrusted data and build agents you’ll actually ship to production using our Python libraries. Observe, govern, and optimize agents written in any language or framework once they’re live.

AI Engineering

Build, run, and improve production AI systems.

Not just Python!Logfire lets you monitor, secure, and optimize agents written in Python, TypeScript, Rust, Go, Java, Ruby, or any other language.

Pydantic Logfire

Observability and governance for AI agents, LLMs, applications, services, and hosts.

logfire.configure();
logfire.info('app started');

See the best AI Engineering platform→

Pydantic AI

The batteries-included type-safe framework for building production agents.

model = 'openai:gpt-5.6-sol'
agent = Agent(model)
agent.run_sync('Does it snow?')

Build production-ready Agents→

Agent Sandboxes

A sandbox for the code your agent writes. No containers or VMs to manage.

sandboxes = logfire.agent_sandboxes()
async with sandboxes as pool:
    async with pool.checkout() as s:
        await s.feed_run('2 ** 10')

Try Agent Sandboxes→

Python Ecosystem

Open source foundations for trusted data, HTTP, and safe code execution.

Pydantic Validation

Data validation from Python type hints. Parse, validate, and serialize with confidence.

class User(BaseModel):
    name: str
    age: int

Learn about Validation→

HTTPX2

A next-generation HTTP client. Sync and async APIs, HTTP/1.1 and HTTP/2.

client = httpx2.Client()
r = client.get('https://pydantic.dev')

Make requests with HTTPX2→

Monty

A minimal, secure Python interpreter in Rust, for running the code your agent writes.

with Monty() as pool:
    with pool.checkout() as s:
        s.feed_run('2 ** 10')

Run agent code safely→