Introduction#

What is AgentPM™ and how it fits into your agent stack.

What is AgentPM™?#

AgentPM is the package layer for agent systems: a spec, a registry, a CLI, and SDKs that make tool, skill, knowledge, memory, profile, loop, agent, and template packages portable across runtimes and host languages.

• The spec (agent.json). A single manifest format for executable tool artifacts, procedural skill artifacts, prepared knowledge artifacts, portable memory blueprint artifacts, authored instruction profile artifacts, declarative loop artifacts, compositional agent artifacts, and reusable template artifacts.
• The package manager & registry. Publish signed package artifacts and install them deterministically with integrity and provenance.
• The CLI. agentpm init/lint/login/publish/install/new/whoami; verify and eval coming soon.
• SDKs (Node & Python). Load tools by name/version, or load installed agents, skills, knowledge packages, memory blueprints, instruction profiles, and loops as inspectable metadata plus resolved package refs. Tools execute in a managed subprocess (with timeouts, env, and resource limits), so there’s no lock-in and no in-process dependency tangle.

Why AgentPM?#

Because agent systems need reusable, versioned building blocks they can trust across stacks and languages. AgentPM gives you:

• tool artifacts for executable capabilities,
• skill artifacts for reusable operational know-how,
• Knowledge artifacts for prepared context and retrieval corpora,
• Memory Blueprint artifacts for durable record contracts and lifecycle declarations,
• Instruction Profile artifacts for portable role, objective, and communication guidance,
• Loop artifacts for portable orchestration structure,
• agent artifacts for portable composition,
• deterministic installs with provenance, and
• adapters/SDKs so one package can move across different agent runtimes and host languages without hand-rolled glue.

Key features#

• agent.json spec for kind: "tool", kind: "skill", kind: "knowledge", kind: "memory", kind: "profile", kind: "loop", kind: "agent", and kind: "template".
• Language-agnostic packaging. Write tools in Node or Python and call them from either SDK.
• Agent package install + load. Install published agent packages and inspect their resolved tool references from the SDKs.
• Load → callable. SDKs turn a tool into a function you can hand to your agent (or call directly).
• Deterministic installs. Versioned artifacts with declared runtime requirements and required environment variables—making agent deployments repeatable.
• Security & provenance. Checksums and signing surfaced in CLI/registry.
• Namespaces & scopes. Public and private namespaces with tokens/MFA.
• Modern search & discovery. Registry search and package pages span tools, skills, knowledge packages, memory blueprints, instruction profiles, agents, templates, and namespaces.
• Current dependency model. Agents can resolve tools, skills, knowledge, memory, profiles, and one loop; skills can resolve tools; templates can reference tools, agents, skills, knowledge, memory, profiles, and one direct loop.
• Verify (coming soon). Manifest-driven contract tests (schema conformance, example runs, invariants, portability matrix, and SLOs). Produces a signed report that gates publish.
• Evals (coming soon). Scenario-level scorecards (accuracy/robustness/latency/cost) that complement verify; results appear on the registry for transparent comparison.

Artifact kinds#

• Tool artifact. Executable package with entrypoint, runtime, inputs/outputs, and packaged files. Tools are what the SDKs actually invoke.
• Skill artifact. Procedural package with a primary SKILL.md entrypoint plus optional references, scripts, and descriptive compatibility metadata.
• Knowledge artifact. Prepared context package for direct context injection or local vector retrieval, depending on knowledge.mode.
• Memory Blueprint artifact. Declarative package for durable record shapes, retrieval semantics, lifecycle policy, and generated resolved contracts.
• Instruction Profile artifact. Authored package for identity, objectives, communication style, boundaries, and constraints.
• Loop artifact. Declarative package for phases, outcomes, transitions, checkpoints, limits, and failure policy.
• Agent artifact. Composition package that captures tool dependencies, example prompts, and package metadata for a reusable agent definition.
• Template packages. Publishable package kinds for reusable workflow starters.

Install the CLI#

macOS & Linux#

brew tap agentpm-dev/tap
brew install agentpm

Windows#

scoop bucket add agentpm https://github.com/agentpm-dev/scoop-bucket
scoop install agentpm