# What is OAP?

> Open Agent Primitives — a secure way to run enterprise AI agents, composed from basic building blocks and run in your own Kubernetes cluster on the models you choose.

Source: https://openap.org/docs/what-is-oap

**Open Agent Primitives (OAP)** is a secure way to run enterprise AI agents. A primitive is a basic
building block that agents rely on, whatever they do; OAP ships a working implementation of each, and agents
are composed from them. It runs in your own Kubernetes cluster on the models you choose. Defining an agent
is easy — a prompt, some tools, a loop. *Operating* one safely is the hard part, and that's what OAP is
for: an agent's identity, authorization, tools, memory, and channels are first-class, governed things rather
than an afterthought.

## The premise

The model is not a trust boundary. A capable agent will be asked to touch real systems — repositories,
dashboards, customer data — and the interesting questions aren't "can it call a tool" but "*whose* credentials
does it use, *may* it do this to *this* resource, *who* approves the risky steps, and *what* did it actually
do." OAP answers those with six composable primitives.

## The six primitives

- **[Agent definition](https://openap.org/docs/agent-definition)** — an agent is a reviewable template (AgentClass) and a disposable
  instance (AgentSession), not a process.
- **[Safe tools](https://openap.org/docs/safe-tools)** — an agent can only do what was written down: sandboxed CLI tools and MCP
  servers, validated against a toolspec.
- **[Identity & credentials](https://openap.org/docs/identity)** — an agent acts as itself or on your behalf, with named credentials
  resolved by need.
- **[Authorization](https://openap.org/docs/authorization)** — every action is checked against a graph: can this subject do this, to
  this resource, right now?
- **[Channels & continuity](https://openap.org/docs/channels)** — agents are reached where teams already work; threads continue and
  approvals live in-channel.
- **[Memory & knowledge](https://openap.org/docs/memory)** — an agent remembers within reason: an authorized, searchable store with a
  knowledge-graph layer.

Each is designed around specific threats from the [OWASP Agentic Top 10](https://openap.org/docs/owasp-top10).

## Where to next

- **[Install OAP](https://openap.org/docs/install-overview)** — bring up the platform, on your Mac or on a cluster.
- **[Your first agent](https://openap.org/docs/quickstart)** — define an agent and talk to it in a few minutes.
