Monty by Pydantic
Hacker ApprovedRanked 4 of 9 Python interpreters by recommenders
Minimal, secure Python interpreter in Rust for untrusted AI-generated code, with serializable state. Critics note Python semantics gaps and the need for another isolation boundary.
Minimal, secure Python interpreter in Rust for untrusted AI-generated code, with serializable state. Critics note Python semantics gaps and the need for another isolation boundary.
18 people gave an opinion
- recommend it
- 15
- criticize it
- 3
- approval share
- 83%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 15 people recommend itNeeds 10 or more, met.
- 5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Serializable VM state, resumable at tool calls
“Monty's VM state is fully serializable so I can run the VM until it gets to a tool call and persist the VM state.”
Comment from 30 Aug 2026 in “monty-go: Pure-Go wrapper for Pydantic's Monty Python Interpreter” “The main property that's really important is that Monty VM state is fully serializable and resumable.”
Comment from 30 Aug 2026 in “monty-go: Pure-Go wrapper for Pydantic's Monty Python Interpreter” Good fit for agent runtimes
“code_execution tool running a workflow of tools inside a python interpreter (monty)”
Comment from 18 Jun 2026 in “The Token Compression Illusion: Why I'm Skeptical of RTK” “that's a very compelling attribute for an agent runtime”
Comment from 30 Aug 2026 in “monty-go: Pure-Go wrapper for Pydantic's Monty Python Interpreter” Minimal design people like
“I like the idea of a minimal implementation like this, though.”
Comment from 6 Feb 2026 in “Monty - A minimal, secure Python interpreter written in Rust” “This is a brilliantly conceived chunk of functionality”
Comment from 7 Feb 2026 in “Python interpreter written in Rust for use by AI” “I like the idea of a minimal implementation like this”
Comment from 7 Feb 2026 in “Monty - A minimal, secure Python interpreter written in Rust” Useful for LLM-generated Python
“Monty is the missing link that's made me ship my rust-based RLM implementation”
Comment from 7 Feb 2026 in “Python interpreter written in Rust for use by AI” “For LLM generated Python code, pydantic's monty is awesome”
Comment from 20 Sep 2026 in “Software sandboxing: The basics (2025)”
What people warn about
Each mark is one comment
Incomplete Python semantics and subset
“The minimal-interpreter approach feels like a good starting point for AI workloads, but the long tail of Python semantics is brutal.”
Comment from 7 Feb 2026 in “Python interpreter written in Rust for use by AI” “a cutdown, less-useful version of Python”
Comment from 7 Feb 2026 in “Python interpreter written in Rust for use by AI” Startup and performance concerns
“loading large compiled executables into memory takes long enough to raise an objection to the "startup times measured in single digit microseconds not hundreds of milliseconds" claim”
Comment from 7 Feb 2026 in “Monty - A minimal, secure Python interpreter written in Rust” “every little papercut at the lower levels of abstraction degrades performance at higher levels”
Comment from 7 Feb 2026 in “Python interpreter written in Rust for use by AI”
Other Python interpreters people recommend
The four most recommended other Python interpreters, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| PyPy | 57 | 34 | 63% | 9 | — | — |
| Pyodide | 31 | 8 | 79% | 9 | — | Approved |
| MicroPython | 25 | 10 | 71% | 10 | — | Approved |
| Monty by PydanticThis page | 15 | 3 | 83% | 5 | — | Approved |
| CircuitPython | 12 | 0 | 100% | 6 | — | Approved |
What people said
23 of the 24 comments that mention it, newest first. Each links to the original comment.
“a joy to work with if you need a way to securely run unverified code”
“supports a Python subset that IMO is sufficient for supporting the plugin sdk”
“For LLM generated Python code, pydantic's monty is awesome”
“Monty makes it feel so native, it even packages a type checker so you can provide stubs for the external functions”
“that's a very compelling attribute for an agent runtime”
“The main property that's really important is that Monty VM state is fully serializable and resumable.”
“Monty's VM state is fully serializable so I can run the VM until it gets to a tool call and persist the VM state.”
“Monty itself seems much more interesting than a Go wrapper”
“code_execution tool running a workflow of tools inside a python interpreter (monty)”
“it does look solid and it has a good team behind it”
“demonstrating how easy and useful it is to be able to turn Rust code into WASM”
“This is a brilliantly conceived chunk of functionality”
“loading large compiled executables into memory takes long enough to raise an objection to the "startup times measured in single digit microseconds not hundreds of milliseconds" claim”
“every little papercut at the lower levels of abstraction degrades performance at higher levels”
“a cutdown, less-useful version of Python”
“although you'd still need another boundary to run your app in to prevent breaking out to other tenants”
“Monty’s overhead is so low that, assuming we get the security / capabilities tradeoff right”
“Monty has too many tradeoffs that makes it non-viable for any real workloads”
“Monty is the missing link that's made me ship my rust-based RLM implementation”
“The minimal-interpreter approach feels like a good starting point for AI workloads, but the long tail of Python semantics is brutal.”
“I like the idea of a minimal implementation like this”
“LLMs that try to use a class will get an error message and rewrite their code”
“I like the idea of a minimal implementation like this, though.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.