{
  "id": "self-managed",
  "title": "Self-managed Redis Agent Memory",
  "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/",
  "summary": "Deploy, configure, secure, and operate Redis Agent Memory on a self-managed Kubernetes cluster.",
  "tags": [
    "docs",
    "develop",
    "ai"
  ],
  "last_updated": "2026-07-28T14:23:48-07:00",
  "children": [
    {
      "id": "plan-deployment",
      "summary": "Choose a self-managed Redis Agent Memory deployment mode before installing the Helm chart.",
      "title": "Plan a self-managed Agent Memory deployment",
      "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/plan-deployment/"
    },
    {
      "id": "prerequisites",
      "summary": "Review software, Redis, network, Secret, image, and sizing prerequisites for self-managed Redis Agent Memory.",
      "title": "Self-managed Agent Memory prerequisites",
      "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/prerequisites/"
    },
    {
      "id": "data-plane-configuration",
      "summary": "Configure the Redis Agent Memory Data Plane for static stores or Control Plane managed stores.",
      "title": "Data Plane configuration",
      "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/data-plane-configuration/"
    },
    {
      "id": "deploy-static",
      "summary": "Deploy Redis Agent Memory with static stores and no Control Plane.",
      "title": "Deploy with static stores",
      "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/deploy-static/"
    },
    {
      "id": "deploy-control-plane",
      "summary": "Deploy Redis Agent Memory with stores managed by the self-managed Control Plane.",
      "title": "Deploy with Control Plane managed stores",
      "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/deploy-control-plane/"
    },
    {
      "id": "authentication",
      "summary": "Configure Redis Agent Memory self-managed Control Plane authentication, Data Plane auth modes, worker callbacks, and gateway integration.",
      "title": "Authentication and authorization",
      "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/authentication/"
    },
    {
      "id": "api-examples",
      "summary": "Use curl examples with the Redis Agent Memory self-managed Control Plane and Data Plane APIs.",
      "title": "Self-managed API examples",
      "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/api-examples/"
    },
    {
      "id": "control-plane-api-reference",
      "summary": "",
      "title": "Redis Agent Memory Control Plane API reference",
      "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/control-plane-api-reference/"
    },
    {
      "id": "operations",
      "summary": "Operate Redis Agent Memory with backups, secret rotation, updates, FIPS posture, and network policy.",
      "title": "Operations",
      "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/operations/"
    },
    {
      "id": "reference",
      "summary": "Review self-managed Redis Agent Memory configuration, troubleshooting guidance, and reference links.",
      "title": "Configuration and troubleshooting",
      "url": "https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/reference/"
    }
  ],
  "page_type": "content",
  "content_hash": "be846c8d6f1c5e5573f0e9fdd8ae8cac0a8f1ce7c0d559fd0337a537b95fc023",
  "sections": [
    {
      "id": "overview",
      "title": "Overview",
      "role": "overview",
      "text": "Redis Agent Memory provides persistent memory for AI agents and\napplications. Applications write conversation events and long-term memories to\nAgent Memory, then query Agent Memory for relevant context before calling an LLM.\n\nThis guide covers deployment, configuration, security, validation, API examples,\nand operations for self-managed Agent Memory.\n\nThe [Redis Agent Memory API](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/api-reference)\nis the shared Data Plane API for Redis Cloud and self-managed deployments. The\n[Control Plane API reference](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/control-plane-api-reference)\ndocuments the self-managed admin endpoints for stores and agent keys.\n\n\nSelf-managed Redis Agent Memory is available as a private preview. You need a\nlicense key to deploy it. Contact your Redis representative or\n[contact sales](https://redis.io/contact/)."
    },
    {
      "id": "what-you-are-deploying",
      "title": "What you are deploying",
      "role": "content",
      "text": "A standard self-managed Agent Memory deployment contains:\n\n| Component | Purpose | Default service |\n| --- | --- | --- |\n| Agent Memory Data Plane | Store-scoped runtime memory API. | `redis-agent-memory:9000` |\n| Agent Memory worker | Background promotion, summarization, and forgetting work. | No public service |\n| Agent Memory Control Plane | Optional admin API for creating stores and managing agent keys. | `redis-agent-memory-controlplane:9100` |\n| Store Redis | Holds session memory, long-term memory, indexes, and TTL data. | Customer-provided |\n| Job Redis | Holds background work for Agent Memory workers. | Customer-provided |\n| Metadata Redis | Holds Control Plane store records and agent-key records. | Required for Control Plane managed stores and agent keys |"
    },
    {
      "id": "how-the-components-work-together",
      "title": "How the components work together",
      "role": "content",
      "text": "The Data Plane handles runtime memory requests. The optional Control Plane\nhandles store and agent-key administration.\n\n| Flow | Caller | Service | Backing Redis |\n| --- | --- | --- | --- |\n| Store and key administration | Platform admin | Agent Memory Control Plane | Metadata Redis |\n| Runtime memory requests | Agent, app, or gateway | Agent Memory Data Plane | Store Redis |\n| Background memory processing | Agent Memory worker | Agent Memory Data Plane | Job Redis and Store Redis |\n\n1. Platform admins use the Control Plane to create stores and agent keys.\n1. The Control Plane stores store records and agent-key grants in Metadata Redis.\n1. Agents and applications call the Data Plane with a store ID.\n1. The Data Plane enforces the configured auth mode and reads or writes memory in Store Redis.\n1. Workers use Job Redis for background work and write generated memory to Store Redis."
    },
    {
      "id": "api-surfaces",
      "title": "API surfaces",
      "role": "content",
      "text": "All Data Plane APIs are scoped to a store. A store is the logical isolation\nboundary for memory data.\n\nWhen agent-key authentication is enabled, grants stored in Metadata Redis\ndetermine which stores and actions each key can access.\n\n| API surface | Endpoint prefix | Purpose |\n| --- | --- | --- |\n| Session memory | `/v1/stores/{storeId}/session-memory` | Ordered conversation events, session metadata, and session lifecycle operations. |\n| Long-term memory | `/v1/stores/{storeId}/long-term-memory` | Searchable facts, preferences, summaries, and custom memory records. |\n| Control Plane | `/v1/stores`, `/v1/api-keys` | Self-managed administration for stores and agent keys. |\n\nSession memory keeps conversation continuity within a session. Long-term memory\nprovides searchable context across sessions.\n\nLong-term memory `memoryType` is an open identifier. When omitted on create,\nAgent Memory stores the record as `semantic`; built-in names include `semantic`,\n`episodic`, `message`, and `session_summary_view`."
    },
    {
      "id": "deployment-modes",
      "title": "Deployment modes",
      "role": "content",
      "text": "Start with [Plan a deployment](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/plan-deployment)\nto choose between static stores and Control Plane managed stores.\n\n| If you need to | Go to |\n| --- | --- |\n| Review software, Redis, network, Secret, image, and sizing requirements | [Prerequisites](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/prerequisites) |\n| Prepare `memory-dataplane.config.yaml` for either deployment mode | [Data Plane configuration](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/data-plane-configuration) |\n| Deploy a first-install or single-store setup without the Control Plane | [Deploy with static stores](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/deploy-static) |\n| Deploy runtime store and agent-key administration | [Deploy with Control Plane managed stores](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/self-managed/deploy-control-plane) |\n\nDo not combine static `metadata.stores` with Control Plane managed store\nmetadata in the same Data Plane config. Static stores do not use Metadata Redis.\nControl Plane managed stores use `metadata.source: live` and require Metadata\nRedis.\n\n\nDo not expose an auth-disabled Data Plane to untrusted callers. In auth-disabled\nmode, Agent Memory does not authenticate or authorize Data Plane requests; any caller that\ncan reach the API can read or write memory for configured stores. Use that mode\nonly when Kubernetes NetworkPolicy, private service exposure, ingress/gateway\npolicy, service mesh, or equivalent controls restrict access to trusted\ncomponents."
    }
  ],
  "examples": []
}