ashishgituser/bunkervm
BunkerVM is a tiny operating system that boots in 2 seconds and gives AI agents a safe, isolated Linux machine to work in. Install it with one command. No Docker. No cloud. No config files.
This project helps AI developers understand and debug their autonomous agents by providing a secure, isolated Linux environment. You can feed your agent's code into this environment and get detailed records of every action, including filesystem changes and VM state. It's designed for developers building and testing AI agents who need precise control and insight into agent behavior.
Available on PyPI.
Use this if you are developing AI agents and need to accurately debug, inspect, or compare their execution by rewinding to any point in time or seeing exactly what files they created or modified.
Not ideal if you just need a basic sandbox for untrusted code execution without deep introspection, or if you're not working with AI agents.
Stars
9
Forks
—
Language
Python
License
AGPL-3.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/ashishgituser/bunkervm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gradion-ai/ipybox
Python code execution sandbox with programmatic MCP tool calling (PTC)
BlackSnufkin/LitterBox
A secure sandbox environment for malware developers and red teamers to test payloads against...
universal-tool-calling-protocol/code-mode
🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
Kiln-AI/Kilntainers
MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.
buremba/1mcp
Let your agent write code and execute code directly in the browser with WASM