§Volume 01 — Welcome

Exo docs

Own your agent infrastructure. Deploy and operate Exo in your own Kubernetes cluster. One platform for agent identity and control, tool credentials and runtime, and end-to-end auditability of every action.

5 min read·Set by Exo Editorial·v0.3.0 Beta

Architecture

A declarative control loop: CRDs define desired state, the operator reconciles them into Kubernetes primitives, and telemetry streams back to the control plane.

  1. 01
    Two components
    Control plane (stateless backend, embedded UI, Postgres) serves the dashboard and API; the Exo Operator and agentkube.io CRDs install into each workload cluster.
  2. 02
    Outbound-only transport
    The operator opens one outbound WebSocket to the control plane, authenticated by a deployment-scoped token. No inbound ports; the connection multiplexes all traffic.
  3. 03
    Declarative API
    Apply Agent and Tool resources via kubectl, GitOps, or the CLI, and inspect them like any native object:
    bash
    1kubectl get agents
    2NAME READY STATUS AGE
    3support-bot 1/1 Running 12d
    4release-notes 1/1 Running 3h
  4. 04
    Reconciliation
    Each resource materializes into Pods, Services, and Secrets; status, heartbeats, shell I/O, and audit stream upstream at sub-second latency.
  5. 05
    Sandboxed tool execution
    Tool calls run in an isolated sandbox; credentials are injected at the boundary and bound to the request, so the agent invokes a tool without ever seeing the underlying secret.
  6. 06
    Identity and audit
    SSO and RBAC gate every operation; Events and Session Recordings form the audit trail; secrets are encrypted at rest under a customer-held key (EXO_ENCRYPTION_KEY).

Audience

For operators deploying and running Exo. Chapters are ordered for that workflow:

  • Start & Deploy — provision the control plane and operator. Start at Components, then Deploy (lead with exo-install).
  • Resources & CRDs — define Agent and Tool custom resources: an Agent spec declares the agent orchestrator and model to use, plus the tools it may call, while a Tool CR describes the executable, its sandbox profile, and the credentials injected at call time. Each resolves to a runtime image the operator runs — an Agent runtime that hosts the model loop and a Tool runtimethat executes calls inside the sandbox, with credentials and permissions bootstrapped at runtime.
  • Identity & access — bind an IdP, define roles and teams, inspect the audit trail.

Find your path