> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/pydantic/monty/llms.txt
> Use this file to discover all available pages before exploring further.

# Monty - Secure Python Sandbox for AI Agents

> A minimal, secure Python interpreter written in Rust with microsecond startup and complete sandbox isolation

<div className="bg-gradient-to-r from-[#df8d6f] to-[#848487] rounded-lg p-8 mb-8">
  <h1 className="text-4xl font-bold text-white mb-4">Monty</h1>
  <p className="text-xl text-white/90">A minimal, secure Python interpreter written in Rust for use by AI agents</p>
</div>

## Why Monty?

Monty lets you safely run LLM-generated Python code embedded in your agent, with startup times measured in single-digit microseconds instead of hundreds of milliseconds. No containers, no complex sandboxing infrastructure — just fast, secure execution.

<CardGroup cols={2}>
  <Card title="Blazing Fast" icon="bolt">
    Sub-microsecond startup time and performance similar to CPython
  </Card>

  <Card title="Completely Isolated" icon="shield">
    Zero access to filesystem, environment, or network without explicit permission
  </Card>

  <Card title="Snapshot & Resume" icon="camera">
    Serialize interpreter state at any point and resume execution later
  </Card>

  <Card title="Multi-Language" icon="code">
    Use from Python, JavaScript/TypeScript, or Rust
  </Card>
</CardGroup>

## Get Started

<CardGroup cols={3}>
  <Card title="Installation" icon="download" href="/installation">
    Install Monty for Python, JavaScript, or Rust
  </Card>

  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Run your first sandboxed Python code in minutes
  </Card>

  <Card title="Core Concepts" icon="book" href="/concepts/security">
    Understand Monty's security model and design
  </Card>
</CardGroup>

## Key Features

<AccordionGroup>
  <Accordion title="Sandboxed Execution">
    Run untrusted Python code with strict security guarantees. Filesystem, network access, and environment variables are all implemented via external function calls you control.
  </Accordion>

  <Accordion title="External Functions">
    Call host functions from sandboxed code. Only functions you explicitly provide are accessible, giving you complete control over I/O operations.
  </Accordion>

  <Accordion title="Type Checking">
    Built-in type checking with ty (from Astral/Ruff) included in a single binary. Catch type errors before execution.
  </Accordion>

  <Accordion title="Resource Limits">
    Track and limit memory usage, allocations, stack depth, and execution time. Cancel execution if it exceeds preset limits.
  </Accordion>

  <Accordion title="Async Support">
    Run async or sync code on the host via async or sync code in the sandbox. Full asyncio support included.
  </Accordion>
</AccordionGroup>

## Use Cases

Monty is designed for one specific use case: **running code written by AI agents**.

<CardGroup cols={2}>
  <Card title="Agent Code Mode" icon="robot" href="/examples/agent-code-mode">
    Let LLMs write Python code instead of using traditional tool calling
  </Card>

  <Card title="Pydantic AI Integration" icon="link" href="/examples/pydantic-ai">
    Use Monty with Pydantic AI for code-mode execution
  </Card>

  <Card title="Web Scraping" icon="globe" href="/examples/web-scraper">
    Safely run LLM-generated web scraping scripts
  </Card>

  <Card title="Data Analysis" icon="chart-line" href="/examples/data-analysis">
    Execute data analysis code written by AI agents
  </Card>
</CardGroup>

## Example

```python theme={null}
from typing import Any
import pydantic_monty

code = """
async def agent(prompt: str, messages: Messages):
    while True:
        output = await call_llm(prompt, messages)
        if isinstance(output, str):
            return output
        messages.extend(output)

await agent(prompt, [])
"""

m = pydantic_monty.Monty(code, inputs=['prompt'], type_check=True)

async def call_llm(prompt: str, messages: list[dict[str, Any]]) -> str | list[dict[str, Any]]:
    if len(messages) < 2:
        return [{'role': 'system', 'content': 'example response'}]
    else:
        return f'example output, message count {len(messages)}'

async def main():
    output = await pydantic_monty.run_monty_async(
        m,
        inputs={'prompt': 'testing'},
        external_functions={'call_llm': call_llm},
    )
    print(output)  # "example output, message count 2"
```

<Card title="View Full API Reference" icon="code" href="/api/python/monty">
  Explore the complete API for Python, JavaScript, and Rust
</Card>