Monty Go

Run LLM-generated Python safely from Go — no containers, no CGO, no subprocess.

LLMs work faster, cheaper, and more reliably when they write code instead of making sequential tool calls. Instead of:

One model call instead of three. The Python code calls your Go functions, Monty pauses at each call, your Go code executes it, and Monty resumes. No containers. No sandbox services. No exec() . Just a 2.9MB WASM binary embedded in your Go binary.

Infinite loops, memory bombs, and deep recursion all terminate cleanly with a *MontyError . Go's context.Context deadlines are also respected — cancel the context and the WASM instance stops.

Monty pauses three times (two searches, one calculation), your Go functions handle each one, and the final result flows back through Gollem's typed output pipeline. Three tool calls in one LLM round-trip.

Gollem gives you compile-time type safety, structured output, guardrails, cost tracking, middleware, and multi-provider support. monty-go gives you secure embedded Python execution. Together, your agents do more work per model call.

No subprocess. The WASM binary is embedded via go:embed and compiled once at startup.

Fresh instance per call. Each Execute() gets an isolated WASM instance. No state leaks between calls.

PEP 448 generalized unpacking ( *args , **kwargs in calls, literals, etc.)