Microsoft Execution Containers (MXC) enforces OS-level boundaries on AI agent access to files, networks, and applications based on developer-defined policies.
It supports process, session, WSL, and MicroVM containment backends across Windows, macOS, and Linux, with Windows 365 support for Cloud PC execution. MXC integrates with Microsoft Entra to separate agent identity from user activity and with Intune to let IT administrators manage and monitor agent workloads.
Learn how Anthropic’s self-hosted sandboxes for Claude Managed Agents allow you to outsource the reasoning while keeping the code execution on your in...
Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), ...
