Why use Pydantic Deep Agents?

Pydantic Deep Agents is a Python framework for building autonomous AI agents with planning, filesystem operations, subagent delegation, and skills. Built on Pydantic AI.

Think of it as the building blocks for creating your own Claude Code, Manus, or Devin-style agents - but open source and self-hosted.

Why use Pydantic Deep Agents?

1. Built on Pydantic AI: Leverages the same ergonomic design that made FastAPI successful - type hints, async/await, and familiar Python patterns.

2. Production Ready: 100% test coverage, strict typing with Pyright + MyPy, and battle-tested in real applications.

3. Modular Architecture: Use the full framework or cherry-pick components. Each capability is an independent package you can use standalone.

4. Secure Execution: Docker sandbox for isolated code execution, permission controls, and human-in-the-loop approval workflows.

Hello World Example

import asyncio
from pydantic_deep import create_deep_agent, DeepAgentDeps, StateBackend

async def main():
    # Create a deep agent with all capabilities
    agent = create_deep_agent(
        model="openai:gpt-4.1",
        instructions="You are a helpful coding assistant.",
    )

    # Create dependencies with in-memory storage
    deps = DeepAgentDeps(backend=StateBackend())

    # Run the agent
    result = await agent.run(
        "Create a Python function that calculates fibonacci numbers",
        deps=deps,
    )

    print(result.output)

asyncio.run(main())

Tools & Dependency Injection Example

from pydantic_ai import RunContext
from pydantic_deep import create_deep_agent, DeepAgentDeps

# Define a custom tool
async def get_weather(
    ctx: RunContext[DeepAgentDeps],
    city: str,
) -> str:
    """Get weather for a city."""
    # Access dependencies via ctx.deps
    return f"Weather in {city}: Sunny, 22°C"

# Create agent with custom tools
agent = create_deep_agent(
    tools=[get_weather],
    instructions="You can check weather and work with files.",
)

Core Capabilities

Modular Ecosystem

Pydantic Deep Agents is built from standalone packages you can use independently:

Installation

pip install pydantic-deep

With Docker sandbox support:

pip install pydantic-deep[sandbox]

llms.txt

Pydantic Deep Agents supports the llms.txt standard. Access documentation at /llms.txt for LLM-optimized content.

Next Steps

• Installation - Get started in minutes
• Core Concepts - Learn about agents, backends, and toolsets
• Examples - See pydantic-deep in action
• API Reference - Complete API documentation