{
"schema_version": 2,
"id": "operate/iris/agent-memory/view-service",
"title": "View and manage Agent Memory service",
"url": "https://redis.io/docs/latest/operate/iris/agent-memory/view-service/",
"summary": "View and manage your Agent Memory service in Redis Cloud.",
"aliases": [
"/operate/rc/context-engine/agent-memory/view-service/",
"/operate/rc/agent-memory/view-service/"
],
"tags": [
"docs",
"operate",
"iris"
],
"last_updated": "2026-10-05T16:11:44+01:00",
"page_type": "content",
"content_hash": "ebd5924eb1ae49551c3f8dbbbde59ee0420fd7b0d4edd87c5a7e9e8539ee4938",
"sections": [
{
"id": "overview",
"title": "Overview",
"role": "overview",
"text": "After you have [created your first Agent Memory service](https://redis.io/docs/latest/operate/iris/agent-memory/create-service), selecting **Agent Memory** from the Redis Cloud Console menu will take you to the **Agent Memory Services** page.\n\nThis page displays a list of all Agent Memory services associated with your account.\n\n\n\nSelect your Agent Memory service from the list to view the service's details."
},
{
"id": "configuration-tab",
"title": "Configuration tab",
"role": "configuration",
"text": "The **Configuration** tab lets you view the details of your Agent Memory service. It contains the following sections:\n\n- The **General settings** section provides the connection details and general settings for your Agent Memory service.\n- The **Memory configuration** section provides the service settings for your Redis Agent Memory service.\n- The **AI model and credentials** section shows the model configuration for a service that uses a customer-managed provider key.\n- The **Memory types & extraction** section shows any custom memory types defined for your service.\n- The **Sensitive-data exclusions** section shows the sensitive-data exclusions configured for your service.\n- The **Actions** section lets you flush or delete your Redis Agent Memory service.\n\nSome of these settings can be changed after service creation. To do so, select the **Edit** button."
},
{
"id": "general-settings",
"title": "General settings",
"role": "content",
"text": "The **General settings** section provides the connection details and general settings for your Agent Memory service.\n\n\n\n| Setting name |Description|\n|:----------------------|:----------|\n| **Service name** | The name of your agent memory service. _(Editable)_ |\n| **Database** | The name of the database your service uses. |\n| **Store ID** | The unique ID of your Agent Memory store. |\n| **Endpoint** | The base URL for any Agent Memory requests. |\n\nSelect the **Copy** button next to the Store ID and API Base URL to copy them to the clipboard.\n\nFollow the [Redis Agent Memory REST API quickstart](https://redis.io/docs/latest/develop/ai/context-engine/agent-memory/rest-api-quickstart) to use the connection information and API key."
},
{
"id": "memory-configuration",
"title": "Memory configuration",
"role": "content",
"text": "The **Memory configuration** section shows the time-to-live (TTL) for memory storage, the extraction cadence, and the automatic summarization settings for session memory.\n\n\n\n| Setting name |Description|\n|:----------------------|:----------|\n| **Short-term TTL** | The time-to-live (TTL) of your agent's **short-term memory** (also known as **session memory**). _(Editable)_ |\n| **Long-term TTL** | The time-to-live (TTL) of your agent's **long-term memory**. _(Editable)_ |\n| **Extraction cadence** | How often the extraction pipeline runs while a session is active. Defaults to 5 minutes; can be set to a value between 60 and 600 seconds. _(Editable)_ |\n| **Automatic summarization** | Whether older messages in a session are automatically compressed into a summary to keep session memory concise during long conversations. _(Editable)_ |\n| **Summarize after (messages)** | The number of messages a session can hold before older messages are summarized. Shown only when automatic summarization is enabled. _(Editable)_ |\n| **Keep most recent (messages)** | The number of most recent messages that are always kept in full and never summarized. Shown only when automatic summarization is enabled. _(Editable)_ |"
},
{
"id": "ai-model-and-credentials",
"title": "AI model and credentials",
"role": "content",
"text": "The **AI model and credentials** section appears when the service uses your model provider key.\n\nProvider and model values shown in the screenshot are examples.\n\n\n\nThe provider and embedding model are read-only. You can change the LLM model or replace the provider key. For update steps, key rotation behavior, security, and troubleshooting guidance, see [Configure AI models for Agent Memory](https://redis.io/docs/latest/operate/iris/agent-memory/model-configuration)."
},
{
"id": "memory-types-and-extraction",
"title": "Memory types & extraction",
"role": "content",
"text": "The **Memory types & extraction** section shows any [custom memory types](https://redis.io/docs/latest/operate/iris/agent-memory/create-service#custom-memory-types) defined for the service, each listed with its name, fields, and extraction strategy.\n\n\n\n#### Custom memory types\n\nBecause a custom memory type's structure is fixed after creation, only some settings can be changed when you edit the service:\n\n| Setting name |Description|\n|:----------------------|:----------|\n| **Name** | The name of the custom memory type. _(Read-only)_ |\n| **Fields** | The fields that make up the custom memory type, with their names, types, and descriptions. _(Read-only)_ |\n| **Extraction prompt** | The extraction strategy prompt for the custom memory type. _(Editable)_ |\n| **Enabled** | Whether the extraction strategy is active. _(Editable)_ |\n\nTo change a custom memory type's name or fields, you must create a new service. You can, however, add a new custom memory type when editing the service, up to the limit of 3 custom memory types."
},
{
"id": "sensitive-data-exclusions",
"title": "Sensitive-data exclusions",
"role": "content",
"text": "The **Sensitive-data exclusions** section shows the [sensitive-data exclusions](https://redis.io/docs/latest/operate/iris/agent-memory/create-service#sensitive-data-exclusions) configured for the service.\n\n> [!NOTE]\n> Sensitive-data exclusions are an early-stage feature, enabled for selected accounts. If you want to try them, contact your Redis representative or [contact sales](https://redis.io/contact/).\n\n\n\n| Setting name |Description|\n|:----------------------|:----------|\n| **Built-in detectors** | Whether built-in detectors are applied, with each selected detector and the action it takes on a match. Only selected detectors are listed. _(Editable)_ |\n| **Custom detectors** | Whether custom detectors are applied, with each detector's name, pattern, action on a match, and status. _(Editable)_ |\n| **Semantic exclusions** | Whether semantic exclusions are applied when memories are extracted. _(Editable)_ |\n| **Exclusion prompt** | The plain-language description of what should never be kept in long-term memory. Required when semantic exclusions are enabled. _(Editable)_ |\n\nTurning semantic exclusions off keeps the exclusion prompt you saved, so you can turn them back on later without retyping it.\n\nChanging exclusions affects memories extracted after you save. Memories already in long-term memory are not re-evaluated, and there is no way to remove only the memories that match your exclusions. The only way to clear memories stored before you configured exclusions is to [flush the service](#flush-memory-entries), which permanently erases all of the service's stored memory data.\n\n> [!WARNING]\n> Semantic exclusions are **advisory**. They steer the extraction model, but they do not guarantee that sensitive content is excluded. Do not rely on semantic exclusions as your only control for regulated or highly sensitive data."
},
{
"id": "actions",
"title": "Actions",
"role": "content",
"text": "The **Actions** section lets you flush or delete your Agent Memory service.\n\n\n\n#### Flush memory entries\n\nFlushing the service completely erases all stored memory data while preserving the service configuration and the search index used by the service.\n\nTo flush the service:\n\n1. Select **Flush**.\n\n1. A confirmation dialog will appear. Select **Flush** again to confirm.\n\nFlushing the service is permanent and cannot be undone, and will result in empty memory retrieval results until new memory is stored.\n\n#### Delete service\n\nDeleting your Agent Memory service permanently deletes all associated memory data, the service configuration, the Agent Memory search index, and any stored model provider key. It also immediately terminates all API keys associated with the service. Data stored in other indexes within the same database will remain unaffected.\n\nTo delete your Agent Memory service:\n\n1. Select **Delete**.\n\n1. A confirmation dialog will appear. Select the checkbox to confirm that you want to delete the service.\n\n1. Select **Delete** again to confirm.\n\nDeleting the Agent Memory service is permanent and cannot be undone."
},
{
"id": "metrics-tab",
"title": "Metrics tab",
"role": "content",
"text": "The **Metrics** tab provides a series of graphs showing performance data for your Agent Memory service.\n\n| Metric | Description |\n|--------|-------------|\n| Short-term Memory Latency | The average time to process a Short-term memory (or Session memory) lookup request. |\n| Long-term Memory Latency | The average time to process a Long-term memory lookup request. |"
},
{
"id": "api-keys-tab",
"title": "API keys tab",
"role": "content",
"text": "The **API keys** tab shows a list of all API keys for your service.\n\n\n\nHere, you can generate a new API key or remove any keys that are no longer in use. You can generate or remove service API keys at any time."
},
{
"id": "replace-service-api-key",
"title": "Generate a new service API key",
"role": "content",
"text": "To generate a new service key:\n\n1. Select **New API key**.\n\n \n\n1. Enter a new name for your API key.\n\n \n\n1. Select **Generate key** to generate your new API key.\n\n1. The new key will appear in a dialog box. Select **Copy** to copy the key to the clipboard.\n\n \n\n > [!WARNING]\n > This is the only time the value of the user key is available. Save it to a secure location before closing the dialog box.
\n >\n > If you lose the service key value, you will need to generate a new key again."
},
{
"id": "delete-api-key",
"title": "Delete API key",
"role": "content",
"text": "To delete an API key, select the **Delete API key** button next to the old key.\n\n"
}
],
"examples": []
}