Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.
AgentDock is a runtime that gives AI agents controlled access to files, commands, Git, browsers, containers, and other tools on local computers and remote servers. It is used to let agents write and test code, manage services, inspect systems, and coordinate work across multiple machines within explicit permissions.
Skill Claude CodeCodex
A guide for creating and maintaining AgentDock skills, which are instruction packages that teach an agent how to handle a specific kind of work.
Skill Claude CodeCodex
A workflow for safely adding a local or third-party skill to AgentDock, a system for managing agent skills. It covers review, installation, configuration, activation, verification, updates, and rollback.
Skill Claude CodeCodex
A user guide for AgentDock, a tool layer that exposes files, commands, Git, browser access, and other capabilities to AI clients such as ChatGPT, Claude, and Codex. It explains installation-specific configuration, connections, restarts, verification, and related services.
Skill Claude CodeCodex
A workflow for obtaining a coding-agent add-on from Git, GitHub, an external catalogue, or another remote source, then handing it to the local installer for checking and installation. It records the source and, where possible, a fixed revision or file digest.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: