monty-go: Pure-Go wrapper for Pydantic's Monty Python Interpreter
Monty-go is a new open-source tool that allows developers to run Python code within Go applications using a sandboxed WebAssembly environment. It aims to improve LLM efficiency by allowing agents to execute code locally rather than relying on sequential tool calls.
Why it matters
It provides a secure, high-performance way to integrate LLM-generated code into backend systems without the overhead of containers.
Run LLM-generated Python safely from Go — no containers, no CGO, no subprocess.
A pure-Go wrapper around Pydantic's Monty Python interpreter, compiled to WebAssembly and loaded via wazero . Your Go agent writes Python code, monty-go executes it in a sandboxed WASM instance with sub-millisecond startup, and pauses whenever the code calls an external function so your Go code can handle it.
go get github.com/fugue-labs/monty-go Why? LLMs work faster, cheaper, and more reliably when they write code instead of making sequential tool calls. Instead of:
Agent → tool_call("search", {query: "weather london"}) → result Agent → tool_call("search", {query: "weather tokyo"}) → result Agent → tool_call("compare", {a: result1, b: result2}) → result The LLM writes:
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in