--- title: Managed Agent Memory Metrics and Alerts Reference description: Reference for the metrics on the Managed Agent Memory monitoring dashboard and the alerts that Capella sends for a Managed Agent Memory server. pubDate: 2026-10-19T14:21:08.937Z meta: component: title: Couchbase Agent Memory version: "1.1" topic_type: reference antora: editUrl: https://github.com/couchbaselabs/docs-agentmemory/edit/release/1.1/modules/reference/pages/metrics-alerts-agent-mem-managed.adoc xref: xref:agent-mem:reference:metrics-alerts-agent-mem-managed.adoc[] --- [Consult the llms.txt file for a full list of contents](/llms.txt) [View original HTML](/agent-mem/current/reference/metrics-alerts-agent-mem-managed.html) # Managed Agent Memory Metrics and Alerts Reference > Reference for the metrics on the Managed Agent Memory monitoring dashboard and the alerts that Capella sends for a Managed Agent Memory server. For how to view the dashboard and receive alerts, see [Monitor Managed Agent Memory](../managed/monitor-agent-mem-managed.md). ## [](#metrics)Metrics The following table lists the Agent Memory server metric behind each card and chart on the [monitoring dashboard](../managed/monitor-agent-mem-managed.md#dashboard). Rates and percentiles use a 5-minute window. | Section | Card or chart | Metric | Calculation | | --------------- | ----------------------------- | ----------------------------------------------------- | ------------------------------------------------------------------------------------------- | | API | Requests total | agentmemory\_requests\_total | Rate per second, summed across endpoints. | | API | API errors total | agentmemory\_api\_errors\_total | Rate per second, summed across status codes. | | API | Blocks added | agentmemory\_blocks\_added\_total | Rate per second, summed across block types. | | API | Request Duration | agentmemory\_request\_duration\_seconds | 99th percentile, for each endpoint. | | API | Tokens per Memory Block | agentmemory\_tokens\_per\_block | 95th percentile, for each type. | | Models & search | Embedding failures | agentmemory\_embedding\_failures\_total | Rate per second. | | Models & search | Context failures | agentmemory\_context\_generation\_failures\_total | Rate per second. | | Models & search | Embedding Generation Duration | agentmemory\_embedding\_generation\_duration\_seconds | 99th percentile, for each model. | | Models & search | Context Generation Duration | agentmemory\_context\_generation\_duration\_seconds | 99th percentile, for each model. | | Ingestion queue | Queue size | agentmemory\_async\_batch\_queue\_size | Sum of queued items across nodes. Items in progress are not included. | | Ingestion queue | Queue capacity | agentmemory\_config\_queue\_max\_size | Sum across nodes. Equals your **Queue max size** setting multiplied by the number of nodes. | | Ingestion queue | Extraction success rate | agentmemory\_async\_batch\_process\_outcomes\_total | Successful outcomes as a share of all outcomes. | | Ingestion queue | Extraction failures | agentmemory\_async\_batch\_process\_outcomes\_total | Rate per second of failed outcomes. | | Ingestion queue | Queue Wait Time | agentmemory\_queue\_wait\_time\_seconds | 99th percentile. | | Ingestion queue | Extraction Duration | agentmemory\_async\_batch\_process\_duration\_seconds | 99th percentile. | | Rate budget | Tokens available | agentmemory\_rate\_budget\_available\_tokens | Sum across nodes. | | Rate budget | Max token budget | agentmemory\_rate\_budget\_max\_tokens | Maximum across nodes. Equals each node's share of your **Tokens per minute** setting. | | Rate budget | Requests available | agentmemory\_rate\_budget\_available\_requests | Sum across nodes. | | Rate budget | Max request budget | agentmemory\_rate\_budget\_max\_requests | Maximum across nodes. Equals each node's share of your **Requests per minute** setting. | | Health | Overall health | agentmemory\_health\_check\_status | Lowest value of the dispatcher, async loop, and database components. 1 means healthy. | | Health | Dispatcher health | agentmemory\_health\_check\_status | Dispatcher component. 1 means healthy. | | Health | Async loop health | agentmemory\_health\_check\_status | Async loop component. 1 means healthy. | | Health | Database health | agentmemory\_health\_check\_status | Database component. 1 means healthy. | | Health | Model health | agentmemory\_health\_check\_status | Lowest value of the embedding model and LLM components. 1 means healthy. | | Health | Live nodes | agentmemory\_cluster\_live\_node\_count | Maximum across nodes. | ## [](#alerts)Alerts Capella sends the following alerts for each Agent Memory server. Capella checks each alert on each node, except the 2 retrieval latency alerts. You cannot change their conditions. | Alert | Severity | Fires when | | --------------------------------------------------------------------------------------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Agent Memory Read/Write Error Rate | Critical | More than 2% of requests return a service error (5xx) over 5 minutes, with at least 10 service errors. | | Agent Memory Model Provider Error Rate | Critical | More than 5% of calls to your embedding model or LLM fail over 5 minutes, with at least 10 errors. Check the status of your model provider and your OpenAI integrations. | | Agent Memory Queue Depth | Critical | The extraction queue, including items in progress, is more than 90% full. When the queue is full, requests to add memory return HTTP 429 with a Retry-After header. | | Agent Memory Model/DB Unreachable | Critical | Your server cannot reach your models or your cluster for more than 5 consecutive health checks. | | Agent Memory Key Revoked | Critical | The OpenAI API key for your embedding model or LLM is deleted or revoked. Your server needs a valid key. | | Agent Memory KV retrieval latency has degraded and requires investigation. | Critical | The 99th percentile latency of key-value reads over 5 minutes is more than twice the 99th percentile for the previous hour, with at least 20 samples. | | Agent Memory semantic search retrieval latency has degraded and requires investigation. | Critical | The 99th percentile latency of semantic search over 5 minutes is more than twice the 99th percentile for the previous hour, with at least 20 samples. | | Agent Memory Custom Prompt Fallback | Warning | Within the last 15 minutes, Agent Memory extracted memory with the default prompt because it could not load a custom prompt. For more information, see [Customize Extraction and Summarization Prompts](../develop/customize-prompts-agent-mem.md). | | Agent Memory Storage Capacity Warning | Warning | A node has used 80% or more of its disk storage. If the disk fills, requests to add memory fail. | ## [](#see-also)See Also * [Monitor Managed Agent Memory](../managed/monitor-agent-mem-managed.md) * [Deploy Managed Agent Memory](../managed/deploy-agent-mem-managed.md)