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 · Cursor · OpenCode · Codex
Documentation · Quick Start · CLI Reference
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.
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 HTTPSgit clone <org/repo> && cd <repo>
apm install # every agent is configuredOne 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, Cursor, OpenCode, Codex
- Install from anywhere — GitHub, GitLab, Bitbucket, Azure DevOps, GitHub Enterprise, 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 packbundles your configuration as a zipped package or a standalone plugin - CI/CD ready — GitHub Action for automated workflows
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 installblocks compromised packages before agents read them;apm auditruns the same checks on demand - Lockfile integrity —
apm.lockrecords resolved sources and content hashes for full provenance - MCP trust boundaries — transitive MCP servers require explicit consent
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.
- 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 --ciinto branch protection
curl -sSL https://aka.ms/apm-unix | shirm https://aka.ms/apm-windows | iexNative release binaries are published for macOS, Linux, and Windows x86_64. apm update reuses the matching platform installer.
Other install methods
# 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-cliThen start adding packages:
apm install microsoft/apm-sample-package#v1.0.0Or install from a marketplace:
apm marketplace add github/awesome-copilot
apm install azure-cloud-development@awesome-copilotOr add an MCP server (wired into Copilot, Claude, Cursor, Codex, and OpenCode):
apm install --mcp io.github.github/github-mcp-server --transport http # connects over HTTPSCodex CLI currently does not support remote MCP servers; the install will skip Codex with a notice. Omit
--transport httpto use the local Docker variant on Codex (requiresGITHUB_PERSONAL_ACCESS_TOKEN).
See the Getting Started guide for the full walkthrough.
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.
Created by @danielmeppiel. Maintained by @danielmeppiel and @sergio-sisternes-epam.
- Roadmap & Discussions
- Contributing
- AI Native Development guide — a practical learning path for AI-native development
Built on open standards: AGENTS.md · Agent Skills · MCP
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.