Self-managed Redis Agent Playbooks
Deploy, configure, and operate Redis Agent Playbooks on a self-managed Kubernetes cluster.
Install Agent Playbooks with the redis-iris suite chart, the supported self-managed install. Installing the redis-agent-playbook chart on its own isn't a supported install path. These guides document its values, which you set under the suite chart's playbook: key.
Redis Agent Playbooks store the answers and procedures your business approves as versioned FAQs and skills, and serve the published versions to your agents. Developers author entries and review proposals in a playbook; agents retrieve published entries over REST or the Model Context Protocol (MCP). Before developers can do that, a platform administrator deploys Agent Playbooks and creates playbooks and agent keys for them.
This guide is for that administrator. It covers deploying Agent Playbooks on your own Kubernetes cluster with a Helm chart, then configuring, securing, and operating it. To install, start with the prerequisites.
The redis-agent-playbook Helm chart deploys the Agent Playbooks control plane and data plane, and optionally a background extraction worker. It connects to a separately installed Identity Service release, which issues and checks agent keys. You provide the Identity Service release, the Redis databases, the embedding provider, and the license. The chart does not install Redis or configure ingress and certificates.
These guides use redis-agent-playbook chart 1.0.0.
Applications call the data plane to author, review, and retrieve entries, as described in the data-plane API reference. The control-plane API reference documents the administration endpoints for playbooks.
What you deploy
| Component | Purpose | Service port |
|---|---|---|
| Control plane | Create playbooks, manage their settings and lifecycle, and validate agent-key grants. | 9200 |
| Data plane | Author and retrieve FAQs and skills, review proposals, and serve MCP requests. | 9201 |
| Extraction worker | Optionally propose FAQs from connected Redis Agent Memory sessions. | 9203 |
| Identity Service | Issue agent keys and check them for the data plane. Installed as its own release. | 9200 |
| Metadata Redis | Store playbook configuration. | Customer-provided |
| Content Redis | Store entries, proposals, and search indexes. Needs JSON and Search. | Customer-provided |
Metadata and content need physically separate Redis deployments.
How the components work together
| Flow | Caller | Service | Backing store |
|---|---|---|---|
| Playbook administration | Platform admin | Control plane | Metadata Redis |
| Agent-key administration | Platform admin | Identity Service | Identity Service metadata Redis |
| Grant validation | Identity Service | Control plane | Metadata Redis |
| Authoring, review, and retrieval | Application or agent | Data plane | Content Redis and the embedding provider |
- Platform admins create playbooks through the control plane, then mint agent keys through the Identity Service.
- The Identity Service asks the control plane to confirm each playbook grant before it stores a key.
- Applications call the data plane with an agent key. The data plane checks the key with the Identity Service and reads or writes the playbook's content.
API surfaces
| API surface | Endpoint | Purpose |
|---|---|---|
| Data plane | /iris/data/v1/agent-playbooks/playbooks/{playbookId} |
Authoring, review, and retrieval for one playbook. |
| MCP | /iris/data/v1/agent-playbooks/playbooks/{playbookId}/mcp |
Read-only MCP tools for agents, on the data-plane port. |
| Control plane | /iris/v1/agent-playbooks/playbooks, /iris/v1/agent-playbooks/models |
Administration of playbooks, their settings, and extraction bindings. |
| Health | /health/liveness, /health/readiness |
Liveness and readiness on both planes. |
| Identity Service | /v1/api-keys |
Administration of agent keys. |
Get started
- Review the prerequisites.
- Prepare the configuration.
- Deploy the chart.
- Load administrative credentials.
- Create a playbook and agent keys.
- Optional: configure background FAQ extraction.