AAaadyachinubhai·Sep 20, 2026
For LLM generated Python code, pydantic's monty is awesome:
https://github.com/pydantic/monty
Plus, pydantic is funded so it will be well maintained.
In Software Sandboxing: The Basics (2025)pydantic
monty
Rust2026–2026
pydantic / monty
monty
A secure Python sandbox, written in Rust, for code written by AI.
13Distinct people
13Mentions
0Explicit recommenders
8.9KGitHub stars
What to know before exploring
What it is
A secure Python sandbox, written in Rust, for code written by AI.
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by month13 dated mentions
Observed mentions: 2026-01-31 17:50:15 UTC to 2026-09-20 23:46:49 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Jan 2026 | 2026-01-01 00:00:00 UTC | 2026-02-01 00:00:00 UTC | 1 | 1 | 0 |
| Feb 2026 | 2026-02-01 00:00:00 UTC | 2026-03-01 00:00:00 UTC | 4 | 3 | 1 |
| Mar 2026 | 2026-03-01 00:00:00 UTC | 2026-04-01 00:00:00 UTC | 3 | 0 | 3 |
| Apr 2026 | 2026-04-01 00:00:00 UTC | 2026-05-01 00:00:00 UTC | 0 | 0 | 0 |
| May 2026 | 2026-05-01 00:00:00 UTC | 2026-06-01 00:00:00 UTC | 1 | 0 | 1 |
| Jun 2026 | 2026-06-01 00:00:00 UTC | 2026-07-01 00:00:00 UTC | 1 | 0 | 1 |
| Jul 2026 | 2026-07-01 00:00:00 UTC | 2026-08-01 00:00:00 UTC | 0 | 0 | 0 |
| Aug 2026 | 2026-08-01 00:00:00 UTC | 2026-09-01 00:00:00 UTC | 1 | 0 | 1 |
| Sep 2026 | 2026-09-01 00:00:00 UTC | 2026-10-01 00:00:00 UTC | 2 | 0 | 2 |
What Hacker News says
13 sourcesSnapshotting programs is also what https://github.com/pydantic/monty enables and aims for.
FWIW, I think we'll see a rise of AI-ready interpreters. In some sense, I like that it challenges traditional microservice architectures as an aside.
In Durable execution without history replayHere are a few examples you might find credible:
- pola-rs/polars: https://github.com/pola-rs/polars/pull/26823 - ~2.68x median speedup of primitive-to-boolean casting credited to Claude Opus 4.6
- pydantic/monty: https://github.com/pydantic/monty/pull/643 - ~53x speedup (488ms down to 9.2ms) of bytes substring search generated with Claude Code
- numpy/numpy: https://github.com/numpy/numpy/pull/31573 - ~21x speedup of Python datetime → datetime64 conversion, with Claude Code used for profiling and implementing the performance improvements
- apache/datafusion: https://github.com/apache/datafusion/pull/21182 - up to 49x speedup of LIMIT queries by eliminating unnecessary sorts and pushing limits into file scans, generated with Claude Code
- apache/datafusion: https://github.com/apache/datafusion/pull/21651 - ~4.39x speedup of ClickBench Q6
Read the rest
by resolving MIN/MAX directly from Parquet metadata instead of scanning columns, generated with Claude Code
- pola-rs/polars: https://github.com/pola-rs/polars/pull/27958 - ~3.2x speedup of Int8 Series sum, developed with assistance from Claude Fable and Claude Opus 4.8
- numpy/numpy: https://github.com/numpy/numpy/pull/31274 - up to ~1.44x speedup of common small NumPy reductions, with the fast path written by Claude Code and manually refined
there's also monty by pydantic https://github.com/pydantic/monty
it's Rust so can be compile to wasm, example: https://github.com/hyper-mcp-rs/monty-plugin
In Running Python code in a sandbox with MicroPython and WASM> Maybe even Python if it can be made safe.
https://github.com/pydantic/monty
In MCP is dead?That’s some fair criticism, but the same page tells that the language wanted to have a similar syntax to C and JavaScript.
I think my personal preference for syntax would be Python’s. One day I want to try writing a query tool with https://github.com/pydantic/monty
In A Faster Alternative to JqBenchmark it against a fast Python interpreter optimized for AI tool calling, like Monty: https://github.com/pydantic/monty
In Executing programs inside transformers with exponentially faster inferenceHey everyone,
I was inspired by Monty and built Zapcode — an open-source TypeScript subset interpreter in Rust, designed for AI agents that write code instead of chaining tool calls.
The problem: AI agents are better when they write code rather than calling tools one by one. Cloudflare (https://blog.cloudflare.com/code-mode/), Anthropic, HuggingFace, and Pydantic are all pushing this pattern. But running AI-generated code is dangerous and slow — Docker adds 200-500ms cold start, V8 isolates bring ~20MB of binary.
Zapcode takes a different approach: a purpose-built bytecode VM that starts in ~2µs, enforces a deny-by-default sandbox at the language level, and can snapshot execution state to <2KB for later resumption.
Instead of three LLM round-trips:
LLM → tool A → LLM → tool B → LLM → tool C → LLM
The LLM writes one code block:
const a = a
Read the rest
wait getWeather("Tokyo");
const b = await getWeather("Paris");
const flights = await searchFlights(a.temp < b.temp ? "Tokyo" : "Paris", ...);
One LLM call, three tool executions. Intermediate values stay in the code, they never pass back through the model.
Key design decisions:
- TypeScript subset, not full TS. Enough for what LLMs generate (variables, functions, classes, async/await, closures, destructuring, 30+ string methods, 25+ array methods) — not enough to be dangerous (no eval, no import, no require, no fs/net/env).
- Sandbox by construction. The core crate has zero std::fs, zero std::net, zero std::env, zero unsafe blocks. The only way out is external functions you explicitly register — when the VM hits one, it suspends and returns a snapshot. Your code resolves the call, not the guest.
- Snapshot/resume. The VM serializes its entire state to bytes (<2KB typical). You can resume in a different process, on a different machine, days
later. This matters for long-running tools (slow API calls, human-in-the-loop approval).
- Embeddable everywhere. Rust, Node.js (napi), Python (PyO3), WebAssembly. No runtime dependencies.
Inspired by Monty (https://github.com/pydantic/monty) which does the same for Python. Zapcode is Monty for TypeScript.
Benchmarks (full pipeline, no caching):
Simple expression: 2.1µs
Function call: 4.6µs
Loop (100 iter): 77.8µs
Fibonacci(10): 138.4µs
Snapshot size: <2KB
Cold start: ~2µs
Source: https://github.com/TheUncharted/zapcode
At this point why not make the agents use a restricted subset of python, typescript or lua or something.
Bash has been unchanged for decades but its not a very nice language.
I know pydantic has been experimenting with https://github.com/pydantic/monty (restricted python) and I think Cloudflare and co were experimenting with giving typescript to agents.
In Just-bash: Bash for AgentsMonty: A minimal, secure Python interpreter written in Rust for use by AI
323 points · Open discussionMonty – A minimal, secure Python interpreter written in Rust for use by AI
4 points · Open discussionMonty: A minimal, secure Python interpreter written in Rust for use by AI
25 points · Open discussionPydantic Monty: A minimal, secure Python interpreter (in Rust) for use by AI
3 points · Open discussion