run_cmd.
How It Works
What You Can Build
AI Agent Code Execution
Execute LLM-generated code in isolated sandboxes
Tool & MCP Server Hosting
Host MCP servers, APIs, or agent tools
Code Interpreter
Build interpreters that execute and iterate
Data Analysis
Process datasets and generate charts
Reinforcement Learning
Run concurrent runtimes for reward evaluation
AI Evaluations
Run test suites in isolated environments
Capabilities
Code Execution
Python and JavaScript with persistent contexts
Terminal
Shell commands, package installs, scripts
File System
Read, write, upload, and download files
Custom Templates
Build environments from any Docker image
Access Runtime
SSH or web terminal access
LLM Integration
Connect LLMs for autonomous execution
Templates
Pre-built templates ready to use. Built on python:3.12-slim.| Template | vCPU | Memory | Disk |
|---|---|---|---|
python-3.12-base-small | 1 | 1 GB | 2 GB |
python-3.12-base-medium | 1 | 2 GB | 4 GB |
python-3.12-base-large | 2 | 4 GB | 8 GB |
Multi-Cloud
| Provider | Region | Status |
|---|---|---|
| Azure | eastus2 (Virginia) | Available |
| AWS | us-east-1 (Virginia) | Coming Soon |
| GCP | us-east1 (South Carolina) | Coming Soon |

