Submit a resource

Navigation

Back to directory

APM Studio

APM Studio is a local GUI for the Agent Package Manager ecosystem that imports agents, skills, prompts, hooks and MCP configurations from GitHub and syncs selected packages out to Codex, Claude, Cursor, Gemini and OpenCode.

Visit website (opens in a new tab)github.com
APM Studio

APM Studio is the visual layer for the Agent Package Manager (APM) ecosystem. It imports source references from a GitHub repository, previews the agent primitives it finds, and installs selected packages locally under a packages directory, keeping canonical package content separate from anything a user edits.

Once imported, a user can edit local package metadata and compose Studio Agents, run those agents locally with Studio-only runtime settings that are never exported to target files, and then export selected agents, instructions, skills, prompts, commands, hooks or MCP configuration into the file formats that Codex, Claude, Cursor, Gemini, OpenCode and other assistants read. It requires Node.js 20.19 or later, OpenCode for running Studio Agents locally, and the separate Microsoft APM CLI for full export coverage, and installs through a shell or PowerShell install script or directly from npm.

More in Agent skills

See all 581

  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents

    github.com

    A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.

Cookies

We use necessary cookies to run the site. Measurement and marketing are optional; neither is used today. Privacy policy