vndee/llm-sandbox

Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

72
/ 100
Verified

This is a developer tool designed for securely executing code generated by Large Language Models (LLMs). It takes in LLM-generated code in various programming languages like Python, JavaScript, Java, C++, Go, or R and runs it in an isolated, controlled environment. The output is the result of the code execution, including any plots or visualizations, without risk to the main system. Developers building AI applications or integrating LLMs into their workflows would use this to ensure safety.

925 stars. Used by 1 other package. Actively maintained with 8 commits in the last 30 days. Available on PyPI.

Use this if you are a developer building an application that uses an LLM to generate code and you need to execute that code safely and reliably without compromising your system's security.

Not ideal if you are an end-user simply interacting with an LLM and do not have a need to manage or execute its generated code programmatically.

AI-application-development LLM-integration code-execution-security AI-safety sandbox-environment
Maintenance 17 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

925

Forks

90

Language

Python

License

MIT

Last pushed

Mar 02, 2026

Commits (30d)

8

Dependencies

1

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/vndee/llm-sandbox"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.