Code on Incus
ActiveDescription
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.
Sandboxed Execution Environment by WithSecure. Designed for malware analysis and security research with virtualization-based isolation, adaptable for AI agent secure execution.
A sandboxed execution environment for AI agents via WASM, providing lightweight and high-performance code isolation for safely executing untrusted agent code.
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
OpenSandbox is an open-source, secure, fast, and extensible sandbox runtime for AI agents, developed by Alibaba.