Agent Memory

import { CardGrid, Description, Feature, LinkButton, LinkTitleCard, RelatedProduct, } from "~/components";

Persistent, scoped memory for agents that need to remember users, organizations, and domain-specific context across conversations.

:::note

Agent Memory is in private beta. To understand the memory model, refer to How Agent Memory works.

:::

Agent Memory gives agents durable memory across conversations without requiring you to build your own extraction, storage, search, and summarization pipeline. Ingest conversations to extract memories automatically, or explicitly remember information when your application already knows what to store.

Use Agent Memory to remember user preferences, company operating rules, support history, project state, or the state of a specific object.

Agent Memory gives you:

• Isolated profiles for users, agents, tenants, teams, or application entities
• Namespaces for separating applications, environments, or memory layers
• Automatic extraction of facts, events, instructions, and tasks from conversations
• APIs to add, list, recall, and delete memories
• Profile summaries for observing what Agent Memory remembers

Get started <LinkButton variant="secondary" href="/agent-memory/concepts/how-agent-memory-works/"

Learn how it works

Features

<Feature
	header="Scoped memory profiles"
	href="/agent-memory/concepts/namespaces-profiles/"
	cta="Learn about profiles"
>

Store memories in isolated profiles for users, agents, teams, tenants, or application entities. Use namespaces to separate applications, environments, or memory layers.

<Feature header="Automatic memory extraction" href="/agent-memory/api/workers-api/#ingest-conversations" cta="Review the API"

Ingest conversations to extract memories automatically, or explicitly add important information when your agent already knows what should be remembered.

<Feature header="Recall memories across agent executions" href="/agent-memory/api/workers-api/#recall-memories" cta="Recall memories"

Retrieve relevant memory when an agent needs durable context that is not present in the current prompt, conversation, or execution.

Related products

Agent Memory is accessed through a Worker binding. Build serverless applications that use persistent memory.

Build AI-powered agents with persistent state, tool use, and real-time communication.

More resources

<LinkTitleCard title="Get started" href="/agent-memory/get-started/" icon="open-book"

Add durable memory recall and ingestion to an agent.

<LinkTitleCard title="How Agent Memory works" href="/agent-memory/concepts/how-agent-memory-works/" icon="document"

Learn how Agent Memory extracts, classifies, and retrieves knowledge from
conversations.

<LinkTitleCard title="Workers API" href="/agent-memory/api/workers-api/" icon="document"

Use Agent Memory from a Worker through an `agent_memory` binding.

<LinkTitleCard title="HTTP API" href="/agent-memory/api/http-api/" icon="document"

Use Agent Memory from services that call the Cloudflare API directly.

<LinkTitleCard title="Limits" href="/agent-memory/platform/limits/" icon="document"

Review validation limits and constraints for Agent Memory.