# llm-in-sandbox

> Computer Environments Elicit General Agentic Intelligence in LLMs

- **URL**: https://www.freshcrate.ai/projects/llm-in-sandbox
- **Author**: llm-in-sandbox
- **Category**: Security
- **Latest version**: `v0.2.0` (2026-02-11)
- **License**: Apache-2.0
- **Source**: https://github.com/llm-in-sandbox/llm-in-sandbox
- **Homepage**: https://arxiv.org/abs/2601.16206
- **Language**: Python
- **GitHub**: 221 stars, 14 forks
- **Registry**: github
- **Tags**: `coding-agent`, `computer-use-agent`, `general-agent`, `python`

## Description

Computer Environments Elicit General Agentic Intelligence in LLMs

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v0.2.0` | 2026-02-11 | Low | ## What's New  ### Benchmark Module - Added benchmark framework to reproduce our paper results and evaluate any LLM/task - Support reward function to facilitate LLM-in-Sandbox-RL - Support for LLM-in-Sandbox and vanilla LLM modes - LLM-as-Judge evaluation  ### Improvements - Restructured README and benchmark docs - Better error handling and Docker cleanup guidance - Clean action, improve observation  ### PyPI - `pip install llm-in-sandbox==0.2.0` |

## Citation

- HTML: https://www.freshcrate.ai/projects/llm-in-sandbox
- Markdown: https://www.freshcrate.ai/projects/llm-in-sandbox.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/llm-in-sandbox/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._