pydantic/monty
A minimal, secure Python interpreter written in Rust for use by AI
About the project
A minimal, secure Python interpreter written in Rust for running code generated by AI models without containers or VMs. It isolates filesystem, network and environment variables, and enforces memory, time and recursion limits.
Useful for
- Run LLM-generated code in a sandbox without Docker or network access
- Enforce memory and time limits on untrusted Python scripts inside the VM
- Serialize a paused interpreter to bytes and resume it later
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 3 stars so far today, about 6 expected by the end of the day.
- GitHub Trending Rust today: #12, +7 stars.
- Recent forks include notable developers: @MarcoGorelli (692 followers).
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 8,266
- Today
- 3 · ≈ 6 by evening
- Forks
- 419
- Issues and pull requests
- 924
- Watchers
- 40
- Language
- Rust
- License
- MIT
- Latest release
- v1.0.0-beta.3 · September 24, 2026
- Created
- May 28, 2023
- Last push
- September 24, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 24, 2026GitHub Trending Rust today: #12, +7 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/pydantic/monty)Similar by description
-
1.6
e2b-dev/runtime
E2B's open-source runtime: the backend that runs isolated Firecracker microVM sandboxes where AI agents execute untrusted code. Includes the API, orchestrator, edge router, and envd inside each VM.
-
1.7
superradcompany/microsandbox
Microsandbox is a local-first runtime and library for running untrusted workloads in fast microVMs with hardware-level isolation. It suits AI agents, user code, plugins, CI jobs, and automation.
-
1.9
TencentCloud/CubeSandbox
High-performance isolated sandbox service built on RustVMM and KVM for running AI agent code: under 60ms cold start, under 5MB memory overhead, E2B SDK compatible.