APM – Agent Package Manager

An open-source, community-driven dependency manager for AI agents.

Think package.json, requirements.txt, or Cargo.toml — but for AI agent configuration.

GitHub Copilot | Claude Code | Grok Build | Cursor | OpenCode | Codex | Gemini | Windsurf | Kiro

Documentation · Quick Start · CLI Reference · v0.29 Roadmap

Portable by manifest. Secure by default. Governed by policy. One file describes every agent's context; one command reproduces it everywhere; one policy controls what an org will allow.

Why APM

AI coding agents need context to be useful — standards, prompts, skills, plugins — but today every developer sets this up manually. Nothing is portable nor reproducible. There's no manifest for it.

APM fixes this. Declare your project's agentic dependencies once in apm.yml, and every developer who clones your repo gets a fully configured agent setup in seconds — with transitive dependency resolution, just like npm or pip. It's also the first tool that lets you author plugins with a real dependency manager and export standard plugin.json packages.

# apm.yml — ships with your project
name: your-project
version: 1.0.0
dependencies:
  apm:
    # Skills from any repository
    - anthropics/skills/skills/frontend-design
    # Plugins
    - github/awesome-copilot/plugins/context-engineering
    # Specific agent primitives from any repository
    - github/awesome-copilot/agents/api-architect.agent.md
    # A full APM package with instructions, skills, prompts, hooks...
    - microsoft/apm-sample-package#v1.0.0
  mcp:
    # MCP servers -- installed into every detected client
    - name: io.github.github/github-mcp-server
      transport: http   # MCP transport name, not URL scheme -- connects over HTTPS

git clone <org/repo> && cd <repo>
apm install    # every agent is configured

Coming from npx skills add? Drop-in:

apm install vercel-labs/agent-skills                            # whole bundle, like npx skills add
apm install vercel-labs/agent-skills --skill deploy-to-vercel   # one skill, persisted to apm.yml

Same install gesture. You also get a manifest, lockfile, and reproducibility.

Zero-config Copilot:

apm compile -t copilot   # writes .github/copilot-instructions.md

One command, no configuration -- VS Code and GitHub Copilot read the file automatically. APM dogfoods this target on its own repository.

The three promises

1. Portable by manifest

One apm.yml describes every primitive your agents need — instructions, skills, prompts, agents, hooks, plugins, MCP servers — and apm install reproduces the exact same setup across every client on every machine. apm.lock.yaml pins the resolved tree the way package-lock.json does for npm.

• One manifest for everything -- declared once, deployed across Copilot, Claude, Grok Build, Cursor, OpenCode, Codex, Gemini, Windsurf, Kiro
• Install from anywhere — GitHub, GitLab, Bitbucket, Azure DevOps, GitHub Enterprise, Gitea, Gogs, any git host
• Transitive dependencies — packages can depend on packages; APM resolves the full tree
• Author plugins — build Copilot, Claude, and Cursor plugins with dependency management, then export standard plugin.json
• Marketplaces — install plugins from curated registries in one command, deployed across all targets and locked
• Pack & distribute — apm pack bundles your configuration as a zipped package or a standalone plugin
• CI/CD ready — GitHub Action for automated workflows

2. Secure by default

Agent context is executable in effect — a prompt is a program for an LLM. APM treats it that way. Every install scans for hidden Unicode that can hijack agent behavior; the lockfile pins integrity hashes; transitive MCP servers are gated by trust prompts.

• Content security — apm install blocks compromised packages before agents read them; apm audit runs the same checks on demand
• Lockfile integrity — apm.lock records resolved sources and content hashes for full provenance
• SBOM export — apm lock export --format cyclonedx|spdx emits a standard inventory of what reached disk, straight from the lockfile — provenance for procurement, not a compliance attestation
• Drift detection — apm audit rebuilds your agent context in scratch and diffs it against your working tree to catch hand-edits before they ship
• MCP trust boundaries — transitive MCP servers require explicit consent

3. Governed by policy

apm-policy.yml lets a security team say "these are the only sources, scopes, and primitives this org will allow" and have every apm install enforce it — with tighten-only inheritance from enterprise to org to repo, a published bypass contract, and audit-mode CI gates.

apm-policy.yml governs what gets installed; your agent harness governs what runs. The two planes do not overlap.

• Governance Guide — the canonical enterprise reference: enforcement points, bypass contract, air-gapped story, failure semantics, rollout playbook
• Policy reference — every check, every field, every default
• Adoption playbook — staged rollout from warn to block across hundreds of repos
• GitHub rulesets integration — wire apm audit --ci into branch protection

Get Started

Linux / macOS

curl -sSL https://aka.ms/apm-unix | sh

Windows

irm https://aka.ms/apm-windows | iex

Native release binaries are published for macOS, Linux, and Windows x86_64. apm self-update reuses the matching platform installer.

# Homebrew
brew install microsoft/apm/apm
# pip
pip install apm-cli

# Scoop
scoop bucket add apm https://github.com/microsoft/scoop-apm
scoop install apm
# pip
pip install apm-cli

Then start adding packages:

apm install microsoft/apm-sample-package#v1.0.0

Or install from a marketplace:

apm marketplace add github/awesome-copilot
apm install azure-cloud-development@awesome-copilot

Or add an MCP server (wired into Copilot, Claude, Cursor, Codex, OpenCode, Gemini, Windsurf, and Kiro):

apm install --mcp io.github.github/github-mcp-server --transport http   # connects over HTTPS

See the Getting Started guide for the full walkthrough.

Works with agentrc

agentrc analyzes your codebase and generates tailored agent instructions — architecture, conventions, build commands — from real code, not templates.

Use agentrc to author high-quality instructions, then package them with APM to share across your org. The .instructions.md format is shared by both tools — no conversion needed when moving instructions into APM packages.

Community

Created by @danielmeppiel. Maintained by @danielmeppiel and @sergio-sisternes-epam.

• v0.29 Roadmap
• Discussions
• Contributing
• AI Native Development guide — a practical learning path for AI-native development

Built on open standards: AGENTS.md · Agent Skills · MCP

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.