RC/AI: Redis Agent Memory by cmilesb · Pull Request #3300 · redis/docs

cmilesb · 2026-05-11T19:47:55Z

Still working on API examples page and service monitoring, but should be updated soon.

Note

Low Risk
Low risk documentation-only change, primarily adding new pages and updating links/aliases; main risk is broken navigation due to the large set of new routes and a likely copy/paste frontmatter title error in agent-memory/api-reference.md.

Overview
Adds a new Context Engine docs section under develop/ai describing LangCache, Agent Memory, Context Retriever, and Data integration, including new getting-started content and a full Agent Memory OpenAPI spec rendered via apireference.

Introduces corresponding Redis Cloud docs under operate/rc/context-engine for LangCache, Agent Memory, and Context Retriever (create/use/view flows, admin key management, embedded setup snippets), and updates existing LangCache docs/changelog/what’s-new links to the new context-engine routes while adding aliases for backward compatibility.

^{Reviewed by Cursor Bugbot for commit 7e3faa2. Bugbot is set up for automated code reviews on this repo. Configure here.}

github-actions · 2026-05-11T19:48:09Z

DOC-6447

github-actions · 2026-05-11T19:48:15Z

jit-ci · 2026-05-11T19:49:01Z

🛡️ Jit Security Scan Results

✅ No security findings were detected in this PR

^{Security scan by Jit}

dwdougherty

So far, so good. Just a few SG-related nitpicks. I can have a look at other pages as you add them if you wish.

dwdougherty · 2026-05-11T19:57:14Z

+The promotion from short term memory to long-term memory is automatic. When you store a conversation event in session memory, the Agent Memory Server asynchronously extracts important information using the configured extraction strategy (discrete, summary, preferences, or custom). These extracted memories are then stored as long-term memory entries with vector embeddings and metadata.
+
+This process is non-blocking: the extraction and promotion happen in the background via a task worker, so the main agent interaction remains responsive. Users do not need to explicitly trigger promotion; it happens as a natural byproduct of storing conversation events in working memory.
+Users can also create long-term memories directly via the API.This is useful for bulk memory creation or for importing knowledge from external sources.


Suggested change

Users can also create long-term memories directly via the API.This is useful for bulk memory creation or for importing knowledge from external sources.

Users can also create long-term memories directly using the API.This is useful for bulk memory creation or for importing knowledge from external sources.

mich-elle-luna

just a few typos, also I think that the agent-memory-service-key.png seems too large on the page.

mich-elle-luna · 2026-05-11T21:05:57Z

thank you, looking great so far!

Co-authored-by: David Dougherty <david.dougherty@redis.com> Co-authored-by: mich-elle-luna <153109578+mich-elle-luna@users.noreply.github.com> Co-authored-by: Cameron Bates <102550101+cmilesb@users.noreply.github.com>

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

dwdougherty

Latest commit looks good, but the API page links need to be more granular: I think you're still working on that content, right?

cmilesb · 2026-05-13T14:06:58Z

Latest commit looks good, but the API page links need to be more granular: I think you're still working on that content, right?

I forgot to update the tags 🤦 That's what I get for pushing things at 6PM. Thanks for the catch.

mich-elle-luna

one comment from a reviewer in devrel team

mich-elle-luna · 2026-05-13T17:26:06Z

+When you call the API, you need to pass the Agent Memory API key in the `Authorization` header as a Bearer token and the store ID as the `storeId` path parameter.
+
+For example:
+


One question from devrel team was if you plan to include a drop-down menu to show programming-language examples, in addition to REST API calls? Just like we have with LangCache? In case of RAM, the Python SDK client?

It's possible to have that, but I haven't had time and I figured I would prioritize getting something out rather than getting something perfect out. I can add that after release (or after I have something for context retriever).

mich-elle-luna · 2026-05-13T18:03:54Z

+### Add session event
+
+Use [`POST /v1/stores/{storeId}/session-memory`]({{< relref "/develop/ai/context-engine/agent-memory/api-reference#tag/session-memory/operation/AddSessionEvent" >}}) to add an event to a session in short-term memory. If a session doesn't exist yet, it will be created.
+


Something Ricardo noticed: It uses cache_id instead of store_id. And the REST API example does the same.

curl -s -X GET "https://$HOST/v1/caches/$CACHE_ID/session-memory/"
-H "accept: application/json"
-H "Authorization: Bearer $API_KEY"

It may be worth double-checking with the API Spec from Agent Memory.

- Add Data Integration as a fourth Context Engine service on the index page - Create develop/ai/context-engine/data-integration/ overview page with get started tabs for Redis Cloud and Redis Enterprise - Remove em dashes and rewrite both pages in Google developer style Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Fix 8 inconsistencies between the hand-written documentation and the Agent Memory OpenAPI spec (MemoryDataPlaneServer): api-examples.md: - Fix curl path: /v1/caches/ -> /v1/stores/ (wrong path segment) - Fix Store ID description typo ("Store ID ID of your cache") - Fix AddSessionEvent endpoint: /session-memory -> /session-memory/events - Fix createdAt format: Unix ms -> ISO 8601 date-time (per MOD-15623) - Fix duplicate namespace row in filter table (second should be topics) - Add missing memoryType filter to the table - Fix createdAt filter data type: integer -> string (ISO 8601) create-service.md: - Fix Long-term TTL description (was copy-pasted from database selector) Verified against the Smithy-generated OpenAPI spec from langcache main (commit fd8b6c2b). Co-authored-by: Cursor <cursoragent@cursor.com>

…s-consistency fix: align Agent Memory docs with current API spec

CLAassistant · 2026-05-15T14:24:28Z

All committers have signed the CLA.

mich-elle-luna

thank you!

atanas-andonov · 2026-05-18T10:25:26Z

+- **Session memory** (also known as **Short-term memory** or **Working memory**) maintains the current conversation state, session history, and session-specific metadata. You can set a custom time-to-live (TTL) for session memory to control how long session data is retained.
+- **Long-term memory** stores information extracted from past sessions, including user preferences, learned patterns, and other relevant data.
+
+The promotion from short term memory to long-term memory is automatic. When you store a conversation event in session memory, the Agent Memory Server asynchronously extracts important information using the configured extraction strategy (discrete, summary, preferences, or custom). These extracted memories are then stored as long-term memory entries with vector embeddings and metadata.


the configured extraction strategy (discrete, summary, preferences, or custom) -> Note here that currently we only support a single extraction strategy that we call instruct internally, but I am thinking we don't even want to specify any strategy names in the docs. Best to confirm with @Jenverse

Suggested change

The promotion from short term memory to long-term memory is automatic. When you store a conversation event in session memory, the Agent Memory Server asynchronously extracts important information using the configured extraction strategy (discrete, summary, preferences, or custom). These extracted memories are then stored as long-term memory entries with vector embeddings and metadata.

The promotion from short term memory to long-term memory is automatic. When you store a conversation event in session memory, the Agent Memory Server asynchronously extracts important information. These extracted memories are then stored as long-term memory entries with vector embeddings and metadata.

atanas-andonov · 2026-05-18T10:29:24Z

+
+-tab-sep-
+
+The open-source version of Redis Agent Memory is [available on GitHub](https://github.com/redis/agent-memory-server). See [Redis Agent Memory server](https://redis.github.io/agent-memory-server/) for comprehensive docs, quick start guides, and API references.


This OSS version of Redis Agent Memory has several differences with the cloud one, and its API is different, so I would double-check again with @Jenverse if we want to promote it here.

atanas-andonov · 2026-05-18T10:33:45Z

+
+Use the [Agent Memory API]({{< relref "/develop/ai/context-engine/agent-memory/api-reference" >}}) from your client app to store and retrieve agent memory information.
+
+You can use any standard REST client or library to access the API. If your app is written in Python, you can also use the [Agent Memory Software Development Kit](https://pypi.org/project/redis-agent-memory/) (SDK) to access the API.


nit - we also have an SDK for Javascript/typescript: https://www.npmjs.com/package/@redis-iris/agent-memory?activeTab=readme

atanas-andonov · 2026-05-18T10:38:12Z

+
+| Setting name          |Description|
+|:----------------------|:----------|
+| **Short-term TTL** | Defines the time-to-live (TTL) of your agent's **short-term memory** (also known as **session memory**). You can define this TTL in seconds, minutes, hours, or days. Default: 1 hour |


nit - we've changed the default to 1 Day at Jen's request (1 hours is also in the screenshot).

RC/AI: Context Retriever

RC/AI: Redis Agent Memory — adds Context Engine section (Agent Memory, Context Retriever, Data Integration) and renames LangCache under it. Upstream merge commit: dfc79b5 Includes sub-PRs: redis#3336 (DOC-6613), redis#3332 (api-docs-consistency)

cmilesb added 3 commits April 24, 2026 11:28

Starting structure for Redis Cloud operator

688b3f8

Agent memory overview 1

108582c

RC/AI: Redis Agent Memory

335576c

cmilesb requested a review from a team May 11, 2026 19:48

cmilesb self-assigned this May 11, 2026

Merge branch 'main' into DOC-6447

7ad9906

dwdougherty reviewed May 11, 2026

View reviewed changes

mich-elle-luna reviewed May 11, 2026

View reviewed changes

Add context engine section and page under develop/ai and operate/rc

1552778

cmilesb commented May 12, 2026

View reviewed changes

Comment thread content/operate/rc/context-engine/agent-memory/create-service.md Outdated

cmilesb commented May 12, 2026

View reviewed changes

Comment thread content/operate/rc/context-engine/agent-memory/create-service.md Outdated

cmilesb commented May 12, 2026

View reviewed changes

Comment thread content/operate/rc/context-engine/agent-memory/view-service.md Outdated

cmilesb and others added 3 commits May 12, 2026 15:42

Apply suggestions from code review

ed69422

Co-authored-by: David Dougherty <david.dougherty@redis.com> Co-authored-by: mich-elle-luna <153109578+mich-elle-luna@users.noreply.github.com> Co-authored-by: Cameron Bates <102550101+cmilesb@users.noreply.github.com>

DOC-6447: Add Context Engine index page

6df35a3

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Add monitoring and API examples

6db28fa

cmilesb requested review from a team, dwdougherty and mich-elle-luna May 12, 2026 21:52

cmilesb marked this pull request as ready for review May 12, 2026 21:52

dwdougherty reviewed May 12, 2026

View reviewed changes

dwdougherty requested a review from a team May 12, 2026 22:16

Add final page and API examples tags.

b3789da

mich-elle-luna reviewed May 13, 2026

View reviewed changes

cmilesb commented May 13, 2026

View reviewed changes

Comment thread content/develop/ai/context-engine/agent-memory/api-examples.md Outdated

Apply suggestion from @cmilesb

362164e

cmilesb commented May 13, 2026

View reviewed changes

Comment thread content/develop/ai/context-engine/agent-memory/api-examples.md Outdated

cmilesb and others added 5 commits May 13, 2026 15:50

Apply suggestion from @cmilesb

605ab98

Update API spec

bc39496

Merge pull request #3332 from atanas-andonov/fix/agent-memory-api-doc…

c94b578

…s-consistency fix: align Agent Memory docs with current API spec

mich-elle-luna requested a review from andy-stark-redis May 15, 2026 14:27

RC/AI: Context Retriever

7d00849

mich-elle-luna approved these changes May 15, 2026

View reviewed changes

mich-elle-luna added 2 commits May 15, 2026 14:57

Fix links for Context Retriever in documentation

4a595fa

remove change to avoid conflict with landing page pr

8a5ed39

atanas-andonov reviewed May 18, 2026

View reviewed changes

Merge pull request #3336 from redis/DOC-6613

7e3faa2

RC/AI: Context Retriever

mich-elle-luna merged commit dfc79b5 into main May 18, 2026
62 checks passed

mich-elle-luna deleted the DOC-6447 branch May 18, 2026 12:44

	Users can also create long-term memories directly via the API.This is useful for bulk memory creation or for importing knowledge from external sources.
	Users can also create long-term memories directly using the API.This is useful for bulk memory creation or for importing knowledge from external sources.

		When you call the API, you need to pass the Agent Memory API key in the `Authorization` header as a Bearer token and the store ID as the `storeId` path parameter.

		For example:

		### Add session event

		Use [`POST /v1/stores/{storeId}/session-memory`]({{< relref "/develop/ai/context-engine/agent-memory/api-reference#tag/session-memory/operation/AddSessionEvent" >}}) to add an event to a session in short-term memory. If a session doesn't exist yet, it will be created.

	The promotion from short term memory to long-term memory is automatic. When you store a conversation event in session memory, the Agent Memory Server asynchronously extracts important information using the configured extraction strategy (discrete, summary, preferences, or custom). These extracted memories are then stored as long-term memory entries with vector embeddings and metadata.
	The promotion from short term memory to long-term memory is automatic. When you store a conversation event in session memory, the Agent Memory Server asynchronously extracts important information. These extracted memories are then stored as long-term memory entries with vector embeddings and metadata.


		-tab-sep-

		The open-source version of Redis Agent Memory is [available on GitHub](https://github.com/redis/agent-memory-server). See [Redis Agent Memory server](https://redis.github.io/agent-memory-server/) for comprehensive docs, quick start guides, and API references.


		Use the [Agent Memory API]({{< relref "/develop/ai/context-engine/agent-memory/api-reference" >}}) from your client app to store and retrieve agent memory information.

		You can use any standard REST client or library to access the API. If your app is written in Python, you can also use the [Agent Memory Software Development Kit](https://pypi.org/project/redis-agent-memory/) (SDK) to access the API.

Conversation

cmilesb commented May 11, 2026 • edited by cursor Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented May 11, 2026 • edited by atlassian Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions Bot commented May 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

jit-ci Bot commented May 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🛡️ Jit Security Scan Results

Uh oh!

dwdougherty left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

mich-elle-luna left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

mich-elle-luna commented May 11, 2026

Uh oh!

Uh oh!

Uh oh!

Uh oh!

dwdougherty left a comment

Choose a reason for hiding this comment

Uh oh!

cmilesb commented May 13, 2026

Uh oh!

mich-elle-luna left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

CLAassistant commented May 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

mich-elle-luna left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

cmilesb commented May 11, 2026 •

edited by cursor Bot

Loading

github-actions Bot commented May 11, 2026 •

edited by atlassian Bot

Loading

github-actions Bot commented May 11, 2026 •

edited

Loading

jit-ci Bot commented May 11, 2026 •

edited

Loading

CLAassistant commented May 15, 2026 •

edited

Loading