> ## 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.

# Introduction

> A minimal, secure Python interpreter written in Rust for use by AI

<Warning>
  **Experimental** - This project is still in development and not ready for prime time.
</Warning>

Monty is a minimal, secure Python interpreter written in Rust specifically designed for running LLM-generated code safely within your agent applications.

## Why Monty?

Monty avoids the cost, latency, complexity, and general faff of using a full container-based sandbox for running LLM-generated code.

Instead, it lets you safely run Python code written by an LLM embedded in your agent, with startup times measured in single digit microseconds — not hundreds of milliseconds.

### The Problem

Large Language Models can work faster, cheaper, and more reliably when they write Python (or JavaScript) code instead of relying on traditional tool calling. However, running untrusted LLM-generated code presents significant security challenges:

* **Containers are slow**: Docker startup takes \~195ms, far too slow for real-time agent interactions
* **Direct execution is dangerous**: Running code via `exec()` or subprocess gives full access to filesystem, network, and system resources
* **WASM solutions are complex**: Options like Pyodide have slow cold starts (\~2.8s) and complex setup requirements

Monty solves this by providing a secure, fast, embedded Python interpreter purpose-built for agent code execution.

## What Monty Can Do

<CardGroup cols={2}>
  <Card title="Run Python Subset" icon="python">
    Execute a reasonable subset of Python code — enough for your agent to express what it wants to do
  </Card>

  <Card title="Secure by Default" icon="shield">
    Completely block access to the host environment: filesystem, env variables, and network access are all implemented via external function calls you control
  </Card>

  <Card title="External Functions" icon="plug">
    Call functions on the host — only functions you explicitly give it access to
  </Card>

  <Card title="Type Checking" icon="check">
    Full modern Python type hints support with [ty](https://docs.astral.sh/ty/) included in a single binary
  </Card>

  <Card title="Snapshotting" icon="camera">
    Snapshot to bytes at external function calls, store interpreter state in a file or database, and resume later
  </Card>

  <Card title="Fast Startup" icon="bolt">
    Startup extremely fast (\<1μs from code to execution result), with runtime performance similar to CPython (generally between 5x faster and 5x slower)
  </Card>

  <Card title="Multi-Language Support" icon="code">
    Call from Rust, Python, or JavaScript — Monty has no dependencies on CPython, so you can use it anywhere you can run Rust
  </Card>

  <Card title="Resource Control" icon="gauge">
    Track memory usage, allocations, stack depth, and execution time — cancel execution if it exceeds preset limits
  </Card>
</CardGroup>

### Additional Features

* Collect stdout and stderr and return it to the caller
* Run async or sync code on the host via async or sync code on the host
* Use a small subset of the standard library: `sys`, `os`, `typing`, `asyncio`, `re`, `datetime` (soon), `dataclasses` (soon), `json` (soon)

## What Monty Cannot Do

<Warning>
  Monty is extremely limited and designed for **one** use case: **to run code written by agents**.
</Warning>

Monty currently does not support:

* The rest of the Python standard library
* Third-party libraries (like Pydantic) — external library support is not a goal
* Class definitions (support coming soon)
* Match statements (support coming soon)

## Use Cases

Monty is designed for agent applications that need to execute LLM-generated code safely:

<CardGroup cols={2}>
  <Card title="Programmatic Tool Calling" icon="tools">
    Replace sequential tool calls with Python code that calls your tools as functions
  </Card>

  <Card title="Agent Code Execution" icon="robot">
    Allow agents to write and execute Python code for complex multi-step tasks
  </Card>

  <Card title="Safe Sandboxing" icon="lock">
    Run untrusted code without containers or risk of host access
  </Card>

  <Card title="PydanticAI Integration" icon="puzzle">
    Power code-mode in [Pydantic AI](https://github.com/pydantic/pydantic-ai) for faster, more reliable agent workflows
  </Card>
</CardGroup>

## Inspiration

For motivation on why you might want to do this, see:

* [Codemode](https://blog.cloudflare.com/code-mode/) from Cloudflare
* [Programmatic Tool Calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling) from Anthropic
* [Code Execution with MCP](https://www.anthropic.com/engineering/code-execution-with-mcp) from Anthropic
* [Smol Agents](https://github.com/huggingface/smolagents) from Hugging Face

<Info>
  Monty will soon be used to implement `codemode` in [Pydantic AI](https://github.com/pydantic/pydantic-ai).
</Info>

## Performance Comparison

| Technology         | Language Completeness | Security | Start Latency | Setup Complexity |
| ------------------ | --------------------- | -------- | ------------- | ---------------- |
| **Monty**          | Partial               | Strict   | **0.06ms**    | Easy             |
| Docker             | Full                  | Good     | 195ms         | Intermediate     |
| Pyodide            | Full                  | Poor     | 2800ms        | Intermediate     |
| WASI/Wasmer        | Partial               | Strict   | 66ms          | Intermediate     |
| Sandboxing Service | Full                  | Strict   | 1033ms        | Intermediate     |

Monty offers the fastest startup time while maintaining strict security guarantees.

## Next Steps

<CardGroup cols={2}>
  <Card title="Installation" icon="download" href="/installation">
    Install Monty for Python, JavaScript, or Rust
  </Card>

  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Get started with your first Monty program
  </Card>
</CardGroup>