Introduction#

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

What is AgentPM™?#

AgentPM is the agent-tooling stack: a spec, a registry, a CLI, and SDKs that make tools runnable by agents—regardless of language.

The spec (agent.json). A single manifest that describes a tool/agent’s inputs & outputs, entrypoint, runtime, environment, and examples. The source of truth for docs, adapters, and conformance checks.
The package manager & registry. Publish signed artifacts; install deterministically with runtime requirements.
The CLI. agentpm init/lint/login/publish/install/whoami; verify and eval coming soon.
SDKs (Node & Python). Load tools by name/version and get functions you can pass to your agent runtime. 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 agents need tools they can trust and reuse—across stacks and languages. AgentPM gives you a tool-centric manifest, deterministic installs with provenance, and adapters/SDKs so a single artifact works across different agent runtimes and host languages—without hand-rolled glue.

Key features#

agent.json spec for kind: "tool" and kind: "agent".
Language-agnostic packaging. Write tools in Node or Python and call them from either SDK.
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. Tool pages auto-generate rich docs from the manifest for fast evaluation and adoption.
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.

Install the CLI#

macOS & Linux#

Homebrew

brew tap agentpm-dev/tap
brew install agentpm

Windows#

Scoop

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

Open-source first

The core of AgentPM—the spec, CLI, and SDKs—is open source. Many tools will be open source too, but you can also publish closed-source tools to the public registry (users can install and run them) and, soon, to private namespaces for your org. The goal is simple: make trustworthy, reusable tools discoverable—OSS or proprietary.