vndee/llm-sandbox
Lightweight and portable LLM sandbox runtime (code interpreter) Python library.
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.
Stars
925
Forks
90
Language
Python
License
MIT
Category
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.
Compare
Related tools
Arize-ai/openinference
OpenTelemetry Instrumentation for AI Observability
apache/hertzbeat
An AI-powered next-generation open source real-time observability system.
traceloop/openllmetry
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
utkuozdemir/nvidia_gpu_exporter
Nvidia GPU exporter for prometheus using nvidia-smi binary
Dynatrace/obslab-llm-observability
Search for a holiday and get destination advice from an LLM. Observability by Dynatrace.