Parassharmaa/agent-sandbox
A sandboxed execution environment for AI agents via WASM
This project provides a secure, isolated environment where you can safely run AI agents that need to execute command-line tools, shell scripts, or JavaScript code. It takes your agent's instructions (like 'run grep' or 'fetch data') and executes them in a controlled space, returning the results. This is for developers building AI agents who need to ensure their agents can interact with system commands and network resources without risking the host system.
Use this if you are building AI agents and need a lightweight, secure way to let them execute commands, scripts, or make HTTP requests without exposing your main system.
Not ideal if your AI agent only performs computations and doesn't require interaction with a shell, filesystem, or external network resources, or if you need to run agents that require a full operating system environment like Docker.
Stars
13
Forks
2
Language
Rust
License
MIT
Category
Last pushed
Feb 10, 2026
Monthly downloads
33
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Parassharmaa/agent-sandbox"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
e2b-dev/E2B
Open-source, secure environment with real-world tools for enterprise-grade agents.
alibaba/OpenSandbox
OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language...
e2b-dev/infra
Infrastructure that's powering E2B Cloud.
always-further/nono
Secure, kernel-enforced sandbox CLI and SDKs for AI agents. Capability-based isolation with...
boxlite-ai/boxlite
Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.