Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.rllm-project.com/llms.txt

Use this file to discover all available pages before exploring further.

Paper

arXiv:2601.16206
LLM-in-Sandbox explores building general-purpose agents by running LLMs inside sandboxed virtual computer environments. It uses rLLM for RL training of agents that interact with full desktop and terminal interfaces.

GitHub repository

View source code