diff --git a/sdk/ai/ai-projects/review/ai-projects-node.api.md b/sdk/ai/ai-projects/review/ai-projects-node.api.md
index 400ee0e93cbd..66bbeaac6681 100644
--- a/sdk/ai/ai-projects/review/ai-projects-node.api.md
+++ b/sdk/ai/ai-projects/review/ai-projects-node.api.md
@@ -1841,7 +1841,7 @@ export interface MemoryStoresOperations {
     list: (options?: MemoryStoresListMemoryStoresOptionalParams) => PagedAsyncIterableIterator<MemoryStore>;
     searchMemories: (name: string, scope: string, options?: MemoryStoresSearchMemoriesOptionalParams) => Promise<MemoryStoreSearchResponse>;
     update: (name: string, options?: MemoryStoresUpdateMemoryStoreOptionalParams) => Promise<MemoryStore>;
-    updateMemories: (name: string, scope: string, options?: MemoryStoresUpdateMemoriesOptionalParams) => PollerLike<OperationState_2<MemoryStoreUpdateResult>, MemoryStoreUpdateResult>;
+    updateMemories: (name: string, scope: string, options?: MemoryStoresUpdateMemoriesOptionalParams) => MemoryStoreUpdateMemoriesPoller;
 }
 
 // @public
@@ -1867,6 +1867,20 @@ export interface MemoryStoresUpdateMemoryStoreOptionalParams extends OperationOp
     metadata?: Record<string, string>;
 }
 
+// @public (undocumented)
+export type MemoryStoreUpdateMemoriesPoller = PollerLike<MemoryStoreUpdateOperationState, MemoryStoreUpdateResult> & {
+    readonly updateId?: string;
+    readonly updateStatus?: MemoryStoreUpdateStatus;
+    readonly supersededBy?: string;
+};
+
+// @public (undocumented)
+export type MemoryStoreUpdateOperationState = OperationState_2<MemoryStoreUpdateResult> & {
+    updateId?: string;
+    updateStatus?: MemoryStoreUpdateStatus;
+    supersededBy?: string;
+};
+
 // @public
 export interface MemoryStoreUpdateResponse {
     error?: ApiError;
diff --git a/sdk/ai/ai-projects/sample.env b/sdk/ai/ai-projects/sample.env
index d8f31b0b4fe2..6e114cefeacf 100644
--- a/sdk/ai/ai-projects/sample.env
+++ b/sdk/ai/ai-projects/sample.env
@@ -1,4 +1,6 @@
 AZURE_AI_PROJECT_ENDPOINT="<project connection string from Microsoft Foundry>"
+AZURE_AI_CHAT_MODEL_DEPLOYMENT_NAME="<memory chat model deployment name>"
+AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME="<memory embedding model deployment name>"
 MODEL_DEPLOYMENT_NAME="<model deployment name>"
 MODEL_API_KEY="<model api key>"
 MODEL_ENDPOINT="<model endpoint url>"
@@ -22,4 +24,3 @@ IMAGE_GENERATION_MODEL_DEPLOYMENT_NAME="<image generation model deployment name>
 
 MCP_PROJECT_CONNECTION_ID="<mcp project connection id>"
 TRIPADVISOR_PROJECT_CONNECTION_ID="<tripadvisor project connection id>"
-
diff --git a/sdk/ai/ai-projects/samples-dev/agents/tools/agentAgentToAgent.ts b/sdk/ai/ai-projects/samples-dev/agents/tools/agentAgentToAgent.ts
index c9a7abf82f20..688aa0d7f091 100644
--- a/sdk/ai/ai-projects/samples-dev/agents/tools/agentAgentToAgent.ts
+++ b/sdk/ai/ai-projects/samples-dev/agents/tools/agentAgentToAgent.ts
@@ -19,7 +19,7 @@ import * as readline from "readline";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const a2aProjectConnectionId =
   process.env["A2A_PROJECT_CONNECTION_ID"] || "<a2a project connection id>";
 
diff --git a/sdk/ai/ai-projects/samples-dev/agents/tools/agentAiSearch.ts b/sdk/ai/ai-projects/samples-dev/agents/tools/agentAiSearch.ts
index f6c6b993993b..6fa4d5cab2bb 100644
--- a/sdk/ai/ai-projects/samples-dev/agents/tools/agentAiSearch.ts
+++ b/sdk/ai/ai-projects/samples-dev/agents/tools/agentAiSearch.ts
@@ -18,7 +18,7 @@ import * as readline from "readline";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const aiSearchConnectionId =
   process.env["AZURE_AI_SEARCH_CONNECTION_ID"] || "<ai search project connection id>";
 const aiSearchIndexName = process.env["AI_SEARCH_INDEX_NAME"] || "<ai search index name>";
diff --git a/sdk/ai/ai-projects/samples-dev/agents/tools/agentBingCustomSearch.ts b/sdk/ai/ai-projects/samples-dev/agents/tools/agentBingCustomSearch.ts
index 19e67fb36d1c..badaa599aa60 100644
--- a/sdk/ai/ai-projects/samples-dev/agents/tools/agentBingCustomSearch.ts
+++ b/sdk/ai/ai-projects/samples-dev/agents/tools/agentBingCustomSearch.ts
@@ -18,7 +18,7 @@ import * as readline from "readline";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const bingCustomSearchProjectConnectionId =
   process.env["BING_CUSTOM_SEARCH_PROJECT_CONNECTION_ID"] ||
   "<bing custom search project connection id>";
diff --git a/sdk/ai/ai-projects/samples-dev/agents/tools/agentBingGrounding.ts b/sdk/ai/ai-projects/samples-dev/agents/tools/agentBingGrounding.ts
index 2af334d68ba8..8857b1e23d6a 100644
--- a/sdk/ai/ai-projects/samples-dev/agents/tools/agentBingGrounding.ts
+++ b/sdk/ai/ai-projects/samples-dev/agents/tools/agentBingGrounding.ts
@@ -17,7 +17,7 @@ import { AIProjectClient } from "@azure/ai-projects";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const bingProjectConnectionId =
   process.env["BING_PROJECT_CONNECTION_ID"] || "<bing project connection id>";
 
diff --git a/sdk/ai/ai-projects/samples-dev/agents/tools/agentBrowserAutomation.ts b/sdk/ai/ai-projects/samples-dev/agents/tools/agentBrowserAutomation.ts
index 9a77b3c8cdf4..1f346031132f 100644
--- a/sdk/ai/ai-projects/samples-dev/agents/tools/agentBrowserAutomation.ts
+++ b/sdk/ai/ai-projects/samples-dev/agents/tools/agentBrowserAutomation.ts
@@ -17,7 +17,7 @@ import { AIProjectClient } from "@azure/ai-projects";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const browserAutomationProjectConnectionId =
   process.env["BROWSER_AUTOMATION_PROJECT_CONNECTION_ID"] ||
   "<browser automation project connection id>";
diff --git a/sdk/ai/ai-projects/samples-dev/agents/tools/agentMemorySearch.ts b/sdk/ai/ai-projects/samples-dev/agents/tools/agentMemorySearch.ts
new file mode 100644
index 000000000000..0147a74fdd1c
--- /dev/null
+++ b/sdk/ai/ai-projects/samples-dev/agents/tools/agentMemorySearch.ts
@@ -0,0 +1,174 @@
+// Copyright (c) Microsoft Corporation.
+// Licensed under the MIT License.
+
+/**
+ * This sample demonstrates how to add conversational memory to an agent by using the
+ * Memory Search tool. The agent stores memories in a memory store and can recall them
+ * in later conversations.
+ *
+ * @summary Create an agent with Memory Search, capture memories from a conversation,
+ * and retrieve them in a new conversation.
+ *
+ * @azsdk-weight 100
+ */
+
+import { DefaultAzureCredential } from "@azure/identity";
+import {
+  AIProjectClient,
+  MemoryStoreDefaultDefinition,
+  MemoryStoreDefaultOptions,
+  MemorySearchTool,
+} from "@azure/ai-projects";
+import "dotenv/config";
+
+const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
+const agentModelDeployment =
+  process.env["MODEL_DEPLOYMENT_NAME"] || "<agent model deployment name>";
+const chatModelDeployment =
+  process.env["AZURE_AI_CHAT_MODEL_DEPLOYMENT_NAME"] || "<memory chat model deployment name>";
+const embeddingModelDeployment =
+  process.env["AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME"] ||
+  "<memory embedding model deployment name>";
+
+const memoryStoreName = "my_memory_store_123";
+const scope = "user_123";
+
+function delay(ms: number): Promise<void> {
+  return new Promise((resolve) => setTimeout(resolve, ms));
+}
+
+export async function main(): Promise<void> {
+  const project = new AIProjectClient(projectEndpoint, new DefaultAzureCredential());
+  const openAIClient = await project.getOpenAIClient();
+
+  let conversationId: string | undefined;
+  let followUpConversationId: string | undefined;
+  let agentVersion:
+    | {
+        name: string;
+        version: string;
+      }
+    | undefined;
+
+  try {
+    // Clean up an existing memory store if it already exists
+    try {
+      await project.memoryStores.delete(memoryStoreName);
+      console.log(`Memory store '${memoryStoreName}' deleted`);
+    } catch (error: any) {
+      if (error?.statusCode !== 404) {
+        throw error;
+      }
+    }
+
+    // Create a memory store with chat and embedding models
+    const memoryStore = await project.memoryStores.create(
+      memoryStoreName,
+      {
+        kind: "default",
+        chat_model: chatModelDeployment,
+        embedding_model: embeddingModelDeployment,
+        options: {
+          user_profile_enabled: true,
+          chat_summary_enabled: true,
+        } satisfies MemoryStoreDefaultOptions,
+      } satisfies MemoryStoreDefaultDefinition,
+      {
+        description: "Memory store for agent conversations",
+      },
+    );
+    const chatModelUsed =
+      "chat_model" in memoryStore.definition
+        ? memoryStore.definition.chat_model
+        : chatModelDeployment;
+    console.log(
+      `Created memory store: ${memoryStore.name} (${memoryStore.id}) using chat model '${chatModelUsed}'`,
+    );
+
+    // Configure Memory Search tool to attach to the agent
+    const memorySearchTool: MemorySearchTool = {
+      type: "memory_search",
+      memory_store_name: memoryStore.name,
+      scope,
+      update_delay: 1, // wait briefly after conversation inactivity before updating memories
+    };
+
+    // Create an agent that will use the Memory Search tool
+    const agent = await project.agents.createVersion("MemorySearchAgent", {
+      kind: "prompt",
+      model: agentModelDeployment,
+      instructions:
+        "You are a helpful assistant that remembers user preferences using the memory search tool.",
+      tools: [memorySearchTool],
+    });
+    agentVersion = {
+      name: agent.name,
+      version: agent.version,
+    };
+    console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${agent.version})`);
+
+    // Start a conversation and provide details the agent should remember
+    const conversation = await openAIClient.conversations.create();
+    conversationId = conversation.id;
+    console.log(`Conversation started (${conversation.id}). Sending a message to seed memories...`);
+
+    const firstResponse = await openAIClient.responses.create(
+      {
+        input: "I prefer dark roast coffee and usually drink it in the morning.",
+        conversation: conversation.id,
+      },
+      {
+        body: { agent: { name: agent.name, type: "agent_reference" } },
+      },
+    );
+    console.log(`Initial response: ${firstResponse.output_text}`);
+
+    // Allow time for the memory store to update from this conversation
+    console.log("Waiting for the memory store to capture the new memory...");
+    await delay(60000);
+
+    // Create a follow-up conversation and ask the agent to recall the stored memory
+    const followUpConversation = await openAIClient.conversations.create();
+    followUpConversationId = followUpConversation.id;
+    console.log(`Follow-up conversation started (${followUpConversation.id}).`);
+
+    const followUpResponse = await openAIClient.responses.create(
+      {
+        input: "Can you remind me of my usual coffee order?",
+        conversation: followUpConversation.id,
+      },
+      {
+        body: { agent: { name: agent.name, type: "agent_reference" } },
+      },
+    );
+    console.log(`Follow-up response: ${followUpResponse.output_text}`);
+  } finally {
+    console.log("\nCleaning up resources...");
+    if (conversationId) {
+      await openAIClient.conversations.delete(conversationId);
+      console.log(`Conversation ${conversationId} deleted`);
+    }
+    if (followUpConversationId) {
+      await openAIClient.conversations.delete(followUpConversationId);
+      console.log(`Conversation ${followUpConversationId} deleted`);
+    }
+    if (agentVersion) {
+      await project.agents.deleteVersion(agentVersion.name, agentVersion.version);
+      console.log("Agent deleted");
+    }
+    try {
+      await project.memoryStores.delete(memoryStoreName);
+      console.log("Memory store deleted");
+    } catch (error: any) {
+      if (error?.statusCode !== 404) {
+        throw error;
+      }
+    }
+  }
+
+  console.log("\nMemory Search agent sample completed!");
+}
+
+main().catch((err) => {
+  console.error("The sample encountered an error:", err);
+});
diff --git a/sdk/ai/ai-projects/samples-dev/agents/tools/agentOpenApi.ts b/sdk/ai/ai-projects/samples-dev/agents/tools/agentOpenApi.ts
index b62167bdc3c3..1ad78e3c404b 100644
--- a/sdk/ai/ai-projects/samples-dev/agents/tools/agentOpenApi.ts
+++ b/sdk/ai/ai-projects/samples-dev/agents/tools/agentOpenApi.ts
@@ -25,7 +25,7 @@ import * as path from "path";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const weatherSpecPath = path.resolve(__dirname, "../assets", "weather_openapi.json");
 
 function loadOpenApiSpec(specPath: string): unknown {
diff --git a/sdk/ai/ai-projects/samples-dev/agents/tools/agentOpenApiConnectionAuth.ts b/sdk/ai/ai-projects/samples-dev/agents/tools/agentOpenApiConnectionAuth.ts
index 1a1402476cf1..cd7d79c13318 100644
--- a/sdk/ai/ai-projects/samples-dev/agents/tools/agentOpenApiConnectionAuth.ts
+++ b/sdk/ai/ai-projects/samples-dev/agents/tools/agentOpenApiConnectionAuth.ts
@@ -25,7 +25,7 @@ import * as path from "path";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const tripAdvisorProjectConnectionId =
   process.env["TRIPADVISOR_PROJECT_CONNECTION_ID"] || "<tripadvisor project connection id>";
 const tripAdvisorSpecPath = path.resolve(__dirname, "../assets", "tripadvisor_openapi.json");
diff --git a/sdk/ai/ai-projects/samples-dev/agents/tools/agentSharepoint.ts b/sdk/ai/ai-projects/samples-dev/agents/tools/agentSharepoint.ts
index 18968483ec87..a5aed4733e39 100644
--- a/sdk/ai/ai-projects/samples-dev/agents/tools/agentSharepoint.ts
+++ b/sdk/ai/ai-projects/samples-dev/agents/tools/agentSharepoint.ts
@@ -17,7 +17,7 @@ import { AIProjectClient } from "@azure/ai-projects";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const sharepointProjectConnectionId =
   process.env["SHAREPOINT_PROJECT_CONNECTION_ID"] || "<sharepoint project connection id>";
 
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/README.md b/sdk/ai/ai-projects/samples/v2-beta/javascript/README.md
index e1d7eae76721..3b68ccf06194 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/javascript/README.md
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/README.md
@@ -27,8 +27,9 @@ These sample programs show how to use the JavaScript client libraries for Azure
 | [agents/tools/agentImageGeneration.js][agents_tools_agentimagegeneration]             | This sample demonstrates how to create an agent with ImageGenTool configured for image generation, make requests to generate images from text prompts, extract base64-encoded image data from the response, decode and save the generated image to a local file, and clean up created resources. |
 | [agents/tools/agentMcp.js][agents_tools_agentmcp]                                     | This sample demonstrates how to create an agent with MCP tool capabilities, send requests that trigger MCP approval workflows, handle approval requests, and clean up resources.                                                                                                                 |
 | [agents/tools/agentMcpConnectionAuth.js][agents_tools_agentmcpconnectionauth]         | This sample demonstrates how to create an agent with MCP tool capabilities using project connection authentication, send requests that trigger MCP approval workflows, handle approval requests, and clean up resources.                                                                         |
+| [agents/tools/agentMemorySearch.js][agents_tools_agentmemorysearch]                   | Create an agent with Memory Search, capture memories from a conversation, and retrieve them in a new conversation.                                                                                                                                                                               |
 | [agents/tools/agentOpenApi.js][agents_tools_agentopenapi]                             | This sample demonstrates how to create an agent with OpenAPI tool capabilities, load OpenAPI specifications from local assets, and process streaming responses that may include tool outputs.                                                                                                    |
-| [agents/tools/agentOpenApiConnectionAuth.js][agents_tools_agentopenapiconnectionauth] | Demonstrates how to create an OpenAPI-enabled agent that uses a project connection for authentication and stream responses that include tool invocation details.                                                                                                                                                     |
+| [agents/tools/agentOpenApiConnectionAuth.js][agents_tools_agentopenapiconnectionauth] | Demonstrates how to create an OpenAPI-enabled agent that uses a project connection for authentication and stream responses that include tool invocation details.                                                                                                                                 |
 | [agents/tools/agentSharepoint.js][agents_tools_agentsharepoint]                       | This sample demonstrates how to create an agent with SharePoint tool capabilities, search SharePoint content, and process streaming responses with citations.                                                                                                                                    |
 | [agents/tools/agentWebSearch.js][agents_tools_agentwebsearch]                         | This sample demonstrates how to create an agent with web search capabilities, send a query to search the web, and clean up resources.                                                                                                                                                            |
 | [responses/responseBasic.js][responses_responsebasic]                                 | This sample demonstrates how to create responses with and without conversation context.                                                                                                                                                                                                          |
@@ -98,6 +99,7 @@ Take a look at our [API Documentation][apiref] for more information about the AP
 [agents_tools_agentimagegeneration]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentImageGeneration.js
 [agents_tools_agentmcp]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentMcp.js
 [agents_tools_agentmcpconnectionauth]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentMcpConnectionAuth.js
+[agents_tools_agentmemorysearch]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentMemorySearch.js
 [agents_tools_agentopenapi]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentOpenApi.js
 [agents_tools_agentopenapiconnectionauth]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentOpenApiConnectionAuth.js
 [agents_tools_agentsharepoint]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentSharepoint.js
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentAgentToAgent.js b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentAgentToAgent.js
index 26a093aac658..57b923bf1a50 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentAgentToAgent.js
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentAgentToAgent.js
@@ -17,7 +17,7 @@ const readline = require("readline");
 require("dotenv/config");
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const a2aProjectConnectionId =
   process.env["A2A_PROJECT_CONNECTION_ID"] || "<a2a project connection id>";
 
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentAiSearch.js b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentAiSearch.js
index 65876cacef3d..f65da47e92c4 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentAiSearch.js
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentAiSearch.js
@@ -16,7 +16,7 @@ const readline = require("readline");
 require("dotenv/config");
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const aiSearchConnectionId =
   process.env["AZURE_AI_SEARCH_CONNECTION_ID"] || "<ai search project connection id>";
 const aiSearchIndexName = process.env["AI_SEARCH_INDEX_NAME"] || "<ai search index name>";
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBingCustomSearch.js b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBingCustomSearch.js
index 2c0717a39eed..06f604778aaa 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBingCustomSearch.js
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBingCustomSearch.js
@@ -16,7 +16,7 @@ const readline = require("readline");
 require("dotenv/config");
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const bingCustomSearchProjectConnectionId =
   process.env["BING_CUSTOM_SEARCH_PROJECT_CONNECTION_ID"] ||
   "<bing custom search project connection id>";
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBingGrounding.js b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBingGrounding.js
index 368adcee489a..cf9c57014b8d 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBingGrounding.js
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBingGrounding.js
@@ -3,7 +3,7 @@
 
 /**
  * This sample demonstrates how to create an AI agent with Bing grounding capabilities
- * using the `bing_grounding` tool type and synchronous Azure AI Projects client. The agent can search
+ * using the "bing_grounding" tool type and synchronous Azure AI Projects client. The agent can search
  * the web for current information and provide grounded responses with URL citations.
  *
  * @summary This sample demonstrates how to create an agent with Bing grounding tool capabilities,
@@ -15,7 +15,7 @@ const { AIProjectClient } = require("@azure/ai-projects");
 require("dotenv/config");
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const bingProjectConnectionId =
   process.env["BING_PROJECT_CONNECTION_ID"] || "<bing project connection id>";
 
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBrowserAutomation.js b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBrowserAutomation.js
index e1cd88fd13f7..2ca6595d1f53 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBrowserAutomation.js
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentBrowserAutomation.js
@@ -15,7 +15,7 @@ const { AIProjectClient } = require("@azure/ai-projects");
 require("dotenv/config");
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const browserAutomationProjectConnectionId =
   process.env["BROWSER_AUTOMATION_PROJECT_CONNECTION_ID"] ||
   "<browser automation project connection id>";
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentMemorySearch.js b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentMemorySearch.js
new file mode 100644
index 000000000000..1a110f8d91bb
--- /dev/null
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentMemorySearch.js
@@ -0,0 +1,164 @@
+// Copyright (c) Microsoft Corporation.
+// Licensed under the MIT License.
+
+/**
+ * This sample demonstrates how to add conversational memory to an agent by using the
+ * Memory Search tool. The agent stores memories in a memory store and can recall them
+ * in later conversations.
+ *
+ * @summary Create an agent with Memory Search, capture memories from a conversation,
+ * and retrieve them in a new conversation.
+ */
+
+const { DefaultAzureCredential } = require("@azure/identity");
+const { AIProjectClient } = require("@azure/ai-projects");
+require("dotenv/config");
+
+const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
+const agentModelDeployment =
+  process.env["MODEL_DEPLOYMENT_NAME"] || "<agent model deployment name>";
+const chatModelDeployment =
+  process.env["AZURE_AI_CHAT_MODEL_DEPLOYMENT_NAME"] || "<memory chat model deployment name>";
+const embeddingModelDeployment =
+  process.env["AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME"] ||
+  "<memory embedding model deployment name>";
+
+const memoryStoreName = "my_memory_store_123";
+const scope = "user_123";
+
+function delay(ms) {
+  return new Promise((resolve) => setTimeout(resolve, ms));
+}
+
+async function main() {
+  const project = new AIProjectClient(projectEndpoint, new DefaultAzureCredential());
+  const openAIClient = await project.getOpenAIClient();
+
+  let conversationId;
+  let followUpConversationId;
+  let agentVersion;
+
+  try {
+    // Clean up an existing memory store if it already exists
+    try {
+      await project.memoryStores.delete(memoryStoreName);
+      console.log(`Memory store '${memoryStoreName}' deleted`);
+    } catch (error) {
+      if (error?.statusCode !== 404) {
+        throw error;
+      }
+    }
+
+    // Create a memory store with chat and embedding models
+    const memoryStore = await project.memoryStores.create(
+      memoryStoreName,
+      {
+        kind: "default",
+        chat_model: chatModelDeployment,
+        embedding_model: embeddingModelDeployment,
+        options: {
+          user_profile_enabled: true,
+          chat_summary_enabled: true,
+        },
+      },
+      {
+        description: "Memory store for agent conversations",
+      },
+    );
+    const chatModelUsed =
+      "chat_model" in memoryStore.definition
+        ? memoryStore.definition.chat_model
+        : chatModelDeployment;
+    console.log(
+      `Created memory store: ${memoryStore.name} (${memoryStore.id}) using chat model '${chatModelUsed}'`,
+    );
+
+    // Configure Memory Search tool to attach to the agent
+    const memorySearchTool = {
+      type: "memory_search",
+      memory_store_name: memoryStore.name,
+      scope,
+      update_delay: 1, // wait briefly after conversation inactivity before updating memories
+    };
+
+    // Create an agent that will use the Memory Search tool
+    const agent = await project.agents.createVersion("MemorySearchAgent", {
+      kind: "prompt",
+      model: agentModelDeployment,
+      instructions:
+        "You are a helpful assistant that remembers user preferences using the memory search tool.",
+      tools: [memorySearchTool],
+    });
+    agentVersion = {
+      name: agent.name,
+      version: agent.version,
+    };
+    console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${agent.version})`);
+
+    // Start a conversation and provide details the agent should remember
+    const conversation = await openAIClient.conversations.create();
+    conversationId = conversation.id;
+    console.log(`Conversation started (${conversation.id}). Sending a message to seed memories...`);
+
+    const firstResponse = await openAIClient.responses.create(
+      {
+        input: "I prefer dark roast coffee and usually drink it in the morning.",
+        conversation: conversation.id,
+      },
+      {
+        body: { agent: { name: agent.name, type: "agent_reference" } },
+      },
+    );
+    console.log(`Initial response: ${firstResponse.output_text}`);
+
+    // Allow time for the memory store to update from this conversation
+    console.log("Waiting for the memory store to capture the new memory...");
+    await delay(60000);
+
+    // Create a follow-up conversation and ask the agent to recall the stored memory
+    const followUpConversation = await openAIClient.conversations.create();
+    followUpConversationId = followUpConversation.id;
+    console.log(`Follow-up conversation started (${followUpConversation.id}).`);
+
+    const followUpResponse = await openAIClient.responses.create(
+      {
+        input: "Can you remind me of my usual coffee order?",
+        conversation: followUpConversation.id,
+      },
+      {
+        body: { agent: { name: agent.name, type: "agent_reference" } },
+      },
+    );
+    console.log(`Follow-up response: ${followUpResponse.output_text}`);
+  } finally {
+    console.log("\nCleaning up resources...");
+    if (conversationId) {
+      await openAIClient.conversations.delete(conversationId);
+      console.log(`Conversation ${conversationId} deleted`);
+    }
+    if (followUpConversationId) {
+      await openAIClient.conversations.delete(followUpConversationId);
+      console.log(`Conversation ${followUpConversationId} deleted`);
+    }
+    if (agentVersion) {
+      await project.agents.deleteVersion(agentVersion.name, agentVersion.version);
+      console.log("Agent deleted");
+    }
+    try {
+      await project.memoryStores.delete(memoryStoreName);
+      console.log("Memory store deleted");
+    } catch (error) {
+      if (error?.statusCode !== 404) {
+        throw error;
+      }
+    }
+  }
+
+  console.log("\nMemory Search agent sample completed!");
+}
+
+main().catch((err) => {
+  console.error("The sample encountered an error:", err);
+});
+
+module.exports = { main };
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentOpenApi.js b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentOpenApi.js
index acaed85db564..ef8d4313010a 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentOpenApi.js
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentOpenApi.js
@@ -18,7 +18,7 @@ const path = require("path");
 require("dotenv/config");
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const weatherSpecPath = path.resolve(__dirname, "../assets", "weather_openapi.json");
 
 function loadOpenApiSpec(specPath) {
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentOpenApiConnectionAuth.js b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentOpenApiConnectionAuth.js
index 410ac3e32331..3bc7cd9dcf4e 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentOpenApiConnectionAuth.js
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentOpenApiConnectionAuth.js
@@ -18,7 +18,7 @@ const path = require("path");
 require("dotenv/config");
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const tripAdvisorProjectConnectionId =
   process.env["TRIPADVISOR_PROJECT_CONNECTION_ID"] || "<tripadvisor project connection id>";
 const tripAdvisorSpecPath = path.resolve(__dirname, "../assets", "tripadvisor_openapi.json");
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentSharepoint.js b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentSharepoint.js
index 23aa9f2444d6..96e6a25f22a9 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentSharepoint.js
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/agents/tools/agentSharepoint.js
@@ -15,7 +15,7 @@ const { AIProjectClient } = require("@azure/ai-projects");
 require("dotenv/config");
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const sharepointProjectConnectionId =
   process.env["SHAREPOINT_PROJECT_CONNECTION_ID"] || "<sharepoint project connection id>";
 
diff --git a/sdk/ai/ai-projects/samples/v2-beta/javascript/sample.env b/sdk/ai/ai-projects/samples/v2-beta/javascript/sample.env
index 376e41be505f..6e114cefeacf 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/javascript/sample.env
+++ b/sdk/ai/ai-projects/samples/v2-beta/javascript/sample.env
@@ -1,4 +1,6 @@
 AZURE_AI_PROJECT_ENDPOINT="<project connection string from Microsoft Foundry>"
+AZURE_AI_CHAT_MODEL_DEPLOYMENT_NAME="<memory chat model deployment name>"
+AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME="<memory embedding model deployment name>"
 MODEL_DEPLOYMENT_NAME="<model deployment name>"
 MODEL_API_KEY="<model api key>"
 MODEL_ENDPOINT="<model endpoint url>"
@@ -21,3 +23,4 @@ FABRIC_PROJECT_CONNECTION_ID="<fabric project connection id>"
 IMAGE_GENERATION_MODEL_DEPLOYMENT_NAME="<image generation model deployment name>"
 
 MCP_PROJECT_CONNECTION_ID="<mcp project connection id>"
+TRIPADVISOR_PROJECT_CONNECTION_ID="<tripadvisor project connection id>"
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/README.md b/sdk/ai/ai-projects/samples/v2-beta/typescript/README.md
index c5a7bdf6feb3..06b7ca9157b0 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/typescript/README.md
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/README.md
@@ -27,8 +27,9 @@ These sample programs show how to use the TypeScript client libraries for Azure
 | [agents/tools/agentImageGeneration.ts][agents_tools_agentimagegeneration]             | This sample demonstrates how to create an agent with ImageGenTool configured for image generation, make requests to generate images from text prompts, extract base64-encoded image data from the response, decode and save the generated image to a local file, and clean up created resources. |
 | [agents/tools/agentMcp.ts][agents_tools_agentmcp]                                     | This sample demonstrates how to create an agent with MCP tool capabilities, send requests that trigger MCP approval workflows, handle approval requests, and clean up resources.                                                                                                                 |
 | [agents/tools/agentMcpConnectionAuth.ts][agents_tools_agentmcpconnectionauth]         | This sample demonstrates how to create an agent with MCP tool capabilities using project connection authentication, send requests that trigger MCP approval workflows, handle approval requests, and clean up resources.                                                                         |
+| [agents/tools/agentMemorySearch.ts][agents_tools_agentmemorysearch]                   | Create an agent with Memory Search, capture memories from a conversation, and retrieve them in a new conversation.                                                                                                                                                                               |
 | [agents/tools/agentOpenApi.ts][agents_tools_agentopenapi]                             | This sample demonstrates how to create an agent with OpenAPI tool capabilities, load OpenAPI specifications from local assets, and process streaming responses that may include tool outputs.                                                                                                    |
-| [agents/tools/agentOpenApiConnectionAuth.ts][agents_tools_agentopenapiconnectionauth] | Demonstrates how to create an OpenAPI-enabled agent that uses a project connection for authentication and stream responses that include tool invocation details.                                                                                                                                                     |
+| [agents/tools/agentOpenApiConnectionAuth.ts][agents_tools_agentopenapiconnectionauth] | Demonstrates how to create an OpenAPI-enabled agent that uses a project connection for authentication and stream responses that include tool invocation details.                                                                                                                                 |
 | [agents/tools/agentSharepoint.ts][agents_tools_agentsharepoint]                       | This sample demonstrates how to create an agent with SharePoint tool capabilities, search SharePoint content, and process streaming responses with citations.                                                                                                                                    |
 | [agents/tools/agentWebSearch.ts][agents_tools_agentwebsearch]                         | This sample demonstrates how to create an agent with web search capabilities, send a query to search the web, and clean up resources.                                                                                                                                                            |
 | [responses/responseBasic.ts][responses_responsebasic]                                 | This sample demonstrates how to create responses with and without conversation context.                                                                                                                                                                                                          |
@@ -110,6 +111,7 @@ Take a look at our [API Documentation][apiref] for more information about the AP
 [agents_tools_agentimagegeneration]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentImageGeneration.ts
 [agents_tools_agentmcp]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentMcp.ts
 [agents_tools_agentmcpconnectionauth]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentMcpConnectionAuth.ts
+[agents_tools_agentmemorysearch]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentMemorySearch.ts
 [agents_tools_agentopenapi]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentOpenApi.ts
 [agents_tools_agentopenapiconnectionauth]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentOpenApiConnectionAuth.ts
 [agents_tools_agentsharepoint]: https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentSharepoint.ts
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/sample.env b/sdk/ai/ai-projects/samples/v2-beta/typescript/sample.env
index 376e41be505f..6e114cefeacf 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/typescript/sample.env
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/sample.env
@@ -1,4 +1,6 @@
 AZURE_AI_PROJECT_ENDPOINT="<project connection string from Microsoft Foundry>"
+AZURE_AI_CHAT_MODEL_DEPLOYMENT_NAME="<memory chat model deployment name>"
+AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME="<memory embedding model deployment name>"
 MODEL_DEPLOYMENT_NAME="<model deployment name>"
 MODEL_API_KEY="<model api key>"
 MODEL_ENDPOINT="<model endpoint url>"
@@ -21,3 +23,4 @@ FABRIC_PROJECT_CONNECTION_ID="<fabric project connection id>"
 IMAGE_GENERATION_MODEL_DEPLOYMENT_NAME="<image generation model deployment name>"
 
 MCP_PROJECT_CONNECTION_ID="<mcp project connection id>"
+TRIPADVISOR_PROJECT_CONNECTION_ID="<tripadvisor project connection id>"
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentAgentToAgent.ts b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentAgentToAgent.ts
index aec32555ead6..20dd4df5d655 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentAgentToAgent.ts
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentAgentToAgent.ts
@@ -17,7 +17,7 @@ import * as readline from "readline";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const a2aProjectConnectionId =
   process.env["A2A_PROJECT_CONNECTION_ID"] || "<a2a project connection id>";
 
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentAiSearch.ts b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentAiSearch.ts
index a9e6a67b8b2e..eeffe0e966cd 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentAiSearch.ts
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentAiSearch.ts
@@ -16,7 +16,7 @@ import * as readline from "readline";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const aiSearchConnectionId =
   process.env["AZURE_AI_SEARCH_CONNECTION_ID"] || "<ai search project connection id>";
 const aiSearchIndexName = process.env["AI_SEARCH_INDEX_NAME"] || "<ai search index name>";
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBingCustomSearch.ts b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBingCustomSearch.ts
index b07445c41b24..4fd47b336142 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBingCustomSearch.ts
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBingCustomSearch.ts
@@ -16,7 +16,7 @@ import * as readline from "readline";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const bingCustomSearchProjectConnectionId =
   process.env["BING_CUSTOM_SEARCH_PROJECT_CONNECTION_ID"] ||
   "<bing custom search project connection id>";
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBingGrounding.ts b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBingGrounding.ts
index 3a6f117862a2..8857b1e23d6a 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBingGrounding.ts
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBingGrounding.ts
@@ -3,7 +3,7 @@
 
 /**
  * This sample demonstrates how to create an AI agent with Bing grounding capabilities
- * using the bing_grounding tool type and synchronous Azure AI Projects client. The agent can search
+ * using the "bing_grounding" tool type and synchronous Azure AI Projects client. The agent can search
  * the web for current information and provide grounded responses with URL citations.
  *
  * @summary This sample demonstrates how to create an agent with Bing grounding tool capabilities,
@@ -17,7 +17,7 @@ import { AIProjectClient } from "@azure/ai-projects";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const bingProjectConnectionId =
   process.env["BING_PROJECT_CONNECTION_ID"] || "<bing project connection id>";
 
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBrowserAutomation.ts b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBrowserAutomation.ts
index 5f264b0f0480..696070c244be 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBrowserAutomation.ts
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentBrowserAutomation.ts
@@ -15,7 +15,7 @@ import { AIProjectClient } from "@azure/ai-projects";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const browserAutomationProjectConnectionId =
   process.env["BROWSER_AUTOMATION_PROJECT_CONNECTION_ID"] ||
   "<browser automation project connection id>";
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentMemorySearch.ts b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentMemorySearch.ts
new file mode 100644
index 000000000000..180b6e032bb5
--- /dev/null
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentMemorySearch.ts
@@ -0,0 +1,172 @@
+// Copyright (c) Microsoft Corporation.
+// Licensed under the MIT License.
+
+/**
+ * This sample demonstrates how to add conversational memory to an agent by using the
+ * Memory Search tool. The agent stores memories in a memory store and can recall them
+ * in later conversations.
+ *
+ * @summary Create an agent with Memory Search, capture memories from a conversation,
+ * and retrieve them in a new conversation.
+ */
+
+import { DefaultAzureCredential } from "@azure/identity";
+import {
+  AIProjectClient,
+  MemoryStoreDefaultDefinition,
+  MemoryStoreDefaultOptions,
+  MemorySearchTool,
+} from "@azure/ai-projects";
+import "dotenv/config";
+
+const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
+const agentModelDeployment =
+  process.env["MODEL_DEPLOYMENT_NAME"] || "<agent model deployment name>";
+const chatModelDeployment =
+  process.env["AZURE_AI_CHAT_MODEL_DEPLOYMENT_NAME"] || "<memory chat model deployment name>";
+const embeddingModelDeployment =
+  process.env["AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME"] ||
+  "<memory embedding model deployment name>";
+
+const memoryStoreName = "my_memory_store_123";
+const scope = "user_123";
+
+function delay(ms: number): Promise<void> {
+  return new Promise((resolve) => setTimeout(resolve, ms));
+}
+
+export async function main(): Promise<void> {
+  const project = new AIProjectClient(projectEndpoint, new DefaultAzureCredential());
+  const openAIClient = await project.getOpenAIClient();
+
+  let conversationId: string | undefined;
+  let followUpConversationId: string | undefined;
+  let agentVersion:
+    | {
+        name: string;
+        version: string;
+      }
+    | undefined;
+
+  try {
+    // Clean up an existing memory store if it already exists
+    try {
+      await project.memoryStores.delete(memoryStoreName);
+      console.log(`Memory store '${memoryStoreName}' deleted`);
+    } catch (error: any) {
+      if (error?.statusCode !== 404) {
+        throw error;
+      }
+    }
+
+    // Create a memory store with chat and embedding models
+    const memoryStore = await project.memoryStores.create(
+      memoryStoreName,
+      {
+        kind: "default",
+        chat_model: chatModelDeployment,
+        embedding_model: embeddingModelDeployment,
+        options: {
+          user_profile_enabled: true,
+          chat_summary_enabled: true,
+        } satisfies MemoryStoreDefaultOptions,
+      } satisfies MemoryStoreDefaultDefinition,
+      {
+        description: "Memory store for agent conversations",
+      },
+    );
+    const chatModelUsed =
+      "chat_model" in memoryStore.definition
+        ? memoryStore.definition.chat_model
+        : chatModelDeployment;
+    console.log(
+      `Created memory store: ${memoryStore.name} (${memoryStore.id}) using chat model '${chatModelUsed}'`,
+    );
+
+    // Configure Memory Search tool to attach to the agent
+    const memorySearchTool: MemorySearchTool = {
+      type: "memory_search",
+      memory_store_name: memoryStore.name,
+      scope,
+      update_delay: 1, // wait briefly after conversation inactivity before updating memories
+    };
+
+    // Create an agent that will use the Memory Search tool
+    const agent = await project.agents.createVersion("MemorySearchAgent", {
+      kind: "prompt",
+      model: agentModelDeployment,
+      instructions:
+        "You are a helpful assistant that remembers user preferences using the memory search tool.",
+      tools: [memorySearchTool],
+    });
+    agentVersion = {
+      name: agent.name,
+      version: agent.version,
+    };
+    console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${agent.version})`);
+
+    // Start a conversation and provide details the agent should remember
+    const conversation = await openAIClient.conversations.create();
+    conversationId = conversation.id;
+    console.log(`Conversation started (${conversation.id}). Sending a message to seed memories...`);
+
+    const firstResponse = await openAIClient.responses.create(
+      {
+        input: "I prefer dark roast coffee and usually drink it in the morning.",
+        conversation: conversation.id,
+      },
+      {
+        body: { agent: { name: agent.name, type: "agent_reference" } },
+      },
+    );
+    console.log(`Initial response: ${firstResponse.output_text}`);
+
+    // Allow time for the memory store to update from this conversation
+    console.log("Waiting for the memory store to capture the new memory...");
+    await delay(60000);
+
+    // Create a follow-up conversation and ask the agent to recall the stored memory
+    const followUpConversation = await openAIClient.conversations.create();
+    followUpConversationId = followUpConversation.id;
+    console.log(`Follow-up conversation started (${followUpConversation.id}).`);
+
+    const followUpResponse = await openAIClient.responses.create(
+      {
+        input: "Can you remind me of my usual coffee order?",
+        conversation: followUpConversation.id,
+      },
+      {
+        body: { agent: { name: agent.name, type: "agent_reference" } },
+      },
+    );
+    console.log(`Follow-up response: ${followUpResponse.output_text}`);
+  } finally {
+    console.log("\nCleaning up resources...");
+    if (conversationId) {
+      await openAIClient.conversations.delete(conversationId);
+      console.log(`Conversation ${conversationId} deleted`);
+    }
+    if (followUpConversationId) {
+      await openAIClient.conversations.delete(followUpConversationId);
+      console.log(`Conversation ${followUpConversationId} deleted`);
+    }
+    if (agentVersion) {
+      await project.agents.deleteVersion(agentVersion.name, agentVersion.version);
+      console.log("Agent deleted");
+    }
+    try {
+      await project.memoryStores.delete(memoryStoreName);
+      console.log("Memory store deleted");
+    } catch (error: any) {
+      if (error?.statusCode !== 404) {
+        throw error;
+      }
+    }
+  }
+
+  console.log("\nMemory Search agent sample completed!");
+}
+
+main().catch((err) => {
+  console.error("The sample encountered an error:", err);
+});
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentOpenApi.ts b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentOpenApi.ts
index 2b78fc0571ba..ff5d62d6467b 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentOpenApi.ts
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentOpenApi.ts
@@ -23,7 +23,7 @@ import * as path from "path";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const weatherSpecPath = path.resolve(__dirname, "../assets", "weather_openapi.json");
 
 function loadOpenApiSpec(specPath: string): unknown {
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentOpenApiConnectionAuth.ts b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentOpenApiConnectionAuth.ts
index 6d9947462cb7..cc17e1968de6 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentOpenApiConnectionAuth.ts
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentOpenApiConnectionAuth.ts
@@ -23,7 +23,7 @@ import * as path from "path";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const tripAdvisorProjectConnectionId =
   process.env["TRIPADVISOR_PROJECT_CONNECTION_ID"] || "<tripadvisor project connection id>";
 const tripAdvisorSpecPath = path.resolve(__dirname, "../assets", "tripadvisor_openapi.json");
diff --git a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentSharepoint.ts b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentSharepoint.ts
index b6fb5e54d83f..f8d60bf2881b 100644
--- a/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentSharepoint.ts
+++ b/sdk/ai/ai-projects/samples/v2-beta/typescript/src/agents/tools/agentSharepoint.ts
@@ -15,7 +15,7 @@ import { AIProjectClient } from "@azure/ai-projects";
 import "dotenv/config";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint>";
-const deploymentName = process.env["AZURE_AI_MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
+const deploymentName = process.env["MODEL_DEPLOYMENT_NAME"] || "<model deployment name>";
 const sharepointProjectConnectionId =
   process.env["SHAREPOINT_PROJECT_CONNECTION_ID"] || "<sharepoint project connection id>";
 
diff --git a/sdk/ai/ai-projects/src/api/memoryStores/index.ts b/sdk/ai/ai-projects/src/api/memoryStores/index.ts
index ac5a33a4bf9a..a93ded24210a 100644
--- a/sdk/ai/ai-projects/src/api/memoryStores/index.ts
+++ b/sdk/ai/ai-projects/src/api/memoryStores/index.ts
@@ -23,3 +23,7 @@ export {
   MemoryStoresUpdateMemoryStoreOptionalParams,
   MemoryStoresCreateMemoryStoreOptionalParams,
 } from "./options.js";
+export {
+  MemoryStoreUpdateMemoriesPoller,
+  MemoryStoreUpdateOperationState,
+} from "./memoryStoreUpdateMemoriesPoller.js";
diff --git a/sdk/ai/ai-projects/src/api/memoryStores/memoryStoreUpdateMemoriesPoller.ts b/sdk/ai/ai-projects/src/api/memoryStores/memoryStoreUpdateMemoriesPoller.ts
new file mode 100644
index 000000000000..3d3a20f6142e
--- /dev/null
+++ b/sdk/ai/ai-projects/src/api/memoryStores/memoryStoreUpdateMemoriesPoller.ts
@@ -0,0 +1,224 @@
+// Copyright (c) Microsoft Corporation.
+// Licensed under the MIT License.
+
+import { AIProjectContext as Client } from "../index.js";
+import {
+  MemoryStoreUpdateResult,
+  MemoryStoreUpdateStatus,
+  MemoryStoreUpdateResponse,
+  memoryStoreUpdateResponseDeserializer,
+  MemoryStoreOperationUsage,
+} from "../../models/models.js";
+import {
+  PollerLike,
+  OperationState,
+  createHttpPoller,
+  RunningOperation,
+  OperationResponse,
+} from "@azure/core-lro";
+import { AbortSignalLike } from "@azure/abort-controller";
+import { PathUncheckedResponse, createRestError } from "@azure-rest/core-client";
+
+export type MemoryStoreUpdateOperationState = OperationState<MemoryStoreUpdateResult> & {
+  updateId?: string;
+  updateStatus?: MemoryStoreUpdateStatus;
+  supersededBy?: string;
+};
+
+export type MemoryStoreUpdateMemoriesPoller = PollerLike<
+  MemoryStoreUpdateOperationState,
+  MemoryStoreUpdateResult
+> & {
+  readonly updateId?: string;
+  readonly updateStatus?: MemoryStoreUpdateStatus;
+  readonly supersededBy?: string;
+};
+
+export interface CreateMemoryStoreUpdateMemoriesPollerOptions {
+  updateIntervalInMs?: number;
+  abortSignal?: AbortSignalLike;
+  restoreFrom?: string;
+}
+
+const terminalUpdateStatuses: MemoryStoreUpdateStatus[] = ["completed", "superseded"];
+
+function createDefaultUsage(): MemoryStoreOperationUsage {
+  return {
+    embedding_tokens: 0,
+    input_tokens: 0,
+    input_tokens_details: { cached_tokens: 0 },
+    output_tokens: 0,
+    output_tokens_details: { reasoning_tokens: 0 },
+    total_tokens: 0,
+  };
+}
+
+function toOperationResponse(
+  response: PathUncheckedResponse,
+  expectedStatuses: string[],
+): OperationResponse<PathUncheckedResponse> {
+  if (!expectedStatuses.includes(response.status)) {
+    throw createRestError(response);
+  }
+
+  return {
+    flatResponse: response,
+    rawResponse: {
+      ...response,
+      statusCode: Number.parseInt(response.status),
+      body: response.body,
+    },
+  };
+}
+
+function deserializeUpdateResponse(
+  response: PathUncheckedResponse,
+): MemoryStoreUpdateResponse | undefined {
+  try {
+    return memoryStoreUpdateResponseDeserializer(response.body);
+  } catch {
+    return undefined;
+  }
+}
+
+function applyUpdateState(
+  state: MemoryStoreUpdateOperationState,
+  response: PathUncheckedResponse,
+): void {
+  const parsed = deserializeUpdateResponse(response);
+  state.updateId ??= parsed?.update_id;
+  state.updateStatus = parsed?.status;
+  state.supersededBy = parsed?.superseded_by;
+
+  if (!parsed) {
+    return;
+  }
+
+  if (parsed.status === "failed") {
+    state.status = "failed";
+    if (!state.error) {
+      state.error = parsed.error
+        ? new Error(parsed.error.message ?? "Memory update failed")
+        : new Error("Memory update failed");
+    }
+    return;
+  }
+
+  if (terminalUpdateStatuses.includes(parsed.status)) {
+    state.status = "succeeded";
+    state.result = parsed.result ??
+      state.result ?? {
+        memory_operations: [],
+        usage: createDefaultUsage(),
+      };
+    return;
+  }
+
+  state.status = "running";
+}
+
+function buildRunningOperation(
+  client: Client,
+  expectedStatuses: string[],
+  getInitialResponse?: () => PromiseLike<PathUncheckedResponse>,
+  options?: CreateMemoryStoreUpdateMemoriesPollerOptions,
+): RunningOperation<PathUncheckedResponse> {
+  const pollAbortController = new AbortController();
+  return {
+    sendInitialRequest: async () => {
+      if (!getInitialResponse) {
+        throw new Error("getInitialResponse is required when starting a new poller");
+      }
+      const initialResponse = await getInitialResponse();
+      return toOperationResponse(initialResponse, expectedStatuses);
+    },
+    sendPollRequest: async (path: string, pollOptions?: { abortSignal?: AbortSignalLike }) => {
+      // The poll request will both listen to the user provided abort signal and the poller's own abort signal
+      function abortListener(): void {
+        pollAbortController.abort();
+      }
+      const abortSignal = pollAbortController.signal;
+      if (options?.abortSignal?.aborted) {
+        pollAbortController.abort();
+      } else if (pollOptions?.abortSignal?.aborted) {
+        pollAbortController.abort();
+      } else if (!abortSignal.aborted) {
+        options?.abortSignal?.addEventListener("abort", abortListener, {
+          once: true,
+        });
+        pollOptions?.abortSignal?.addEventListener("abort", abortListener, {
+          once: true,
+        });
+      }
+
+      let response: PathUncheckedResponse;
+      try {
+        response = (await client.pathUnchecked(path).get({ abortSignal })) as PathUncheckedResponse;
+      } finally {
+        options?.abortSignal?.removeEventListener("abort", abortListener);
+        pollOptions?.abortSignal?.removeEventListener("abort", abortListener);
+      }
+
+      return toOperationResponse(response, expectedStatuses);
+    },
+  };
+}
+
+export function createMemoryStoreUpdateMemoriesPoller(
+  client: Client,
+  expectedStatuses: string[],
+  getInitialResponse?: () => PromiseLike<PathUncheckedResponse>,
+  options: CreateMemoryStoreUpdateMemoriesPollerOptions = {},
+): MemoryStoreUpdateMemoriesPoller {
+  if (!getInitialResponse && !options?.restoreFrom) {
+    throw new Error("getInitialResponse is required when starting a new poller");
+  }
+  let initialResponse: PathUncheckedResponse | undefined;
+
+  const poller = createHttpPoller<MemoryStoreUpdateResult, MemoryStoreUpdateOperationState>(
+    buildRunningOperation(
+      client,
+      expectedStatuses,
+      getInitialResponse
+        ? async () => {
+            initialResponse = await getInitialResponse();
+            return initialResponse;
+          }
+        : undefined,
+      options,
+    ),
+    {
+      intervalInMs: options?.updateIntervalInMs,
+      restoreFrom: options?.restoreFrom,
+      updateState: (state, lastResponse) => {
+        const flatResponse = lastResponse.flatResponse as PathUncheckedResponse;
+        applyUpdateState(state, flatResponse);
+      },
+      processResult: async (operationResponse, state) => {
+        applyUpdateState(state, operationResponse as PathUncheckedResponse);
+        return state.result as MemoryStoreUpdateResult;
+      },
+    },
+  ) as MemoryStoreUpdateMemoriesPoller;
+
+  if (initialResponse && poller.operationState) {
+    applyUpdateState(poller.operationState, initialResponse);
+  }
+
+  Object.defineProperties(poller, {
+    updateId: {
+      enumerable: true,
+      get: () => poller.operationState?.updateId,
+    },
+    updateStatus: {
+      enumerable: true,
+      get: () => poller.operationState?.updateStatus,
+    },
+    supersededBy: {
+      enumerable: true,
+      get: () => poller.operationState?.supersededBy,
+    },
+  });
+
+  return poller;
+}
diff --git a/sdk/ai/ai-projects/src/api/memoryStores/operations.ts b/sdk/ai/ai-projects/src/api/memoryStores/operations.ts
index 2f7e4351bfb4..2e7262a4dbbd 100644
--- a/sdk/ai/ai-projects/src/api/memoryStores/operations.ts
+++ b/sdk/ai/ai-projects/src/api/memoryStores/operations.ts
@@ -18,8 +18,6 @@ import {
   memoryStoreSearchResponseDeserializer,
   MemoryStoreUpdateResponse,
   memoryStoreUpdateResponseDeserializer,
-  MemoryStoreUpdateResult,
-  MemoryStoreUpdateResultDeserializer,
   MemoryStoreDeleteScopeResponse,
   memoryStoreDeleteScopeResponseDeserializer,
 } from "../../models/models.js";
@@ -27,8 +25,11 @@ import {
   PagedAsyncIterableIterator,
   buildPagedAsyncIterator,
 } from "../../static-helpers/pagingHelpers.js";
-import { getLongRunningPoller } from "../../static-helpers/pollingHelpers.js";
 import { expandUrlTemplate } from "../../static-helpers/urlTemplate.js";
+import {
+  createMemoryStoreUpdateMemoriesPoller,
+  MemoryStoreUpdateMemoriesPoller,
+} from "./memoryStoreUpdateMemoriesPoller.js";
 import {
   MemoryStoresDeleteScopeOptionalParams,
   MemoryStoresGetUpdateResultOptionalParams,
@@ -46,7 +47,6 @@ import {
   createRestError,
   operationOptionsToRequestParameters,
 } from "@azure-rest/core-client";
-import { PollerLike, OperationState } from "@azure/core-lro";
 
 export function _deleteScopeSend(
   context: Client,
@@ -182,38 +182,22 @@ export function _updateMemoriesSend(
   });
 }
 
-export async function _updateMemoriesDeserialize(
-  result: PathUncheckedResponse,
-): Promise<MemoryStoreUpdateResult> {
-  const expectedStatuses = ["202", "200"];
-  if (!expectedStatuses.includes(result.status)) {
-    const error = createRestError(result);
-    error.details = apiErrorResponseDeserializer(result.body);
-    throw error;
-  }
-
-  if (result?.body?.result === undefined) {
-    throw createRestError(
-      `Expected a result in the response at position "result.body.result"`,
-      result,
-    );
-  }
-
-  return MemoryStoreUpdateResultDeserializer(result.body.result);
-}
-
 /** Update memory store with conversation memories. */
 export function updateMemories(
   context: Client,
   name: string,
   scope: string,
   options: MemoryStoresUpdateMemoriesOptionalParams = { requestOptions: {} },
-): PollerLike<OperationState<MemoryStoreUpdateResult>, MemoryStoreUpdateResult> {
-  return getLongRunningPoller(context, _updateMemoriesDeserialize, ["202", "200"], {
-    updateIntervalInMs: options?.updateIntervalInMs,
-    abortSignal: options?.abortSignal,
-    getInitialResponse: () => _updateMemoriesSend(context, name, scope, options),
-  }) as PollerLike<OperationState<MemoryStoreUpdateResult>, MemoryStoreUpdateResult>;
+): MemoryStoreUpdateMemoriesPoller {
+  return createMemoryStoreUpdateMemoriesPoller(
+    context,
+    ["202", "200"],
+    () => _updateMemoriesSend(context, name, scope, options),
+    {
+      updateIntervalInMs: options?.updateIntervalInMs,
+      abortSignal: options?.abortSignal,
+    },
+  );
 }
 
 export function _searchMemoriesSend(
diff --git a/sdk/ai/ai-projects/src/classic/memoryStores/index.ts b/sdk/ai/ai-projects/src/classic/memoryStores/index.ts
index dc64faa23a17..4cb540464477 100644
--- a/sdk/ai/ai-projects/src/classic/memoryStores/index.ts
+++ b/sdk/ai/ai-projects/src/classic/memoryStores/index.ts
@@ -30,11 +30,10 @@ import {
   DeleteMemoryStoreResponse,
   MemoryStoreSearchResponse,
   MemoryStoreUpdateResponse,
-  MemoryStoreUpdateResult,
   MemoryStoreDeleteScopeResponse,
 } from "../../models/models.js";
+import { MemoryStoreUpdateMemoriesPoller } from "../../api/memoryStores/memoryStoreUpdateMemoriesPoller.js";
 import { PagedAsyncIterableIterator } from "../../static-helpers/pagingHelpers.js";
-import { PollerLike, OperationState } from "@azure/core-lro";
 
 /** Interface representing a MemoryStores operations. */
 export interface MemoryStoresOperations {
@@ -55,7 +54,7 @@ export interface MemoryStoresOperations {
     name: string,
     scope: string,
     options?: MemoryStoresUpdateMemoriesOptionalParams,
-  ) => PollerLike<OperationState<MemoryStoreUpdateResult>, MemoryStoreUpdateResult>;
+  ) => MemoryStoreUpdateMemoriesPoller;
   /** Search for relevant memories from a memory store based on conversation context. */
   searchMemories: (
     name: string,
diff --git a/sdk/ai/ai-projects/src/index.ts b/sdk/ai/ai-projects/src/index.ts
index 8262d65b0a6a..9bed70de0a81 100644
--- a/sdk/ai/ai-projects/src/index.ts
+++ b/sdk/ai/ai-projects/src/index.ts
@@ -404,6 +404,10 @@ export {
   MemoryStoresUpdateMemoryStoreOptionalParams,
   MemoryStoresCreateMemoryStoreOptionalParams,
 } from "./api/memoryStores/index.js";
+export {
+  MemoryStoreUpdateMemoriesPoller,
+  MemoryStoreUpdateOperationState,
+} from "./api/memoryStores/memoryStoreUpdateMemoriesPoller.js";
 export {
   RedTeamsCreateOptionalParams,
   RedTeamsListOptionalParams,
diff --git a/sdk/ai/ai-projects/src/restorePollerHelpers.ts b/sdk/ai/ai-projects/src/restorePollerHelpers.ts
index 0a961506e05b..db852dd0652c 100644
--- a/sdk/ai/ai-projects/src/restorePollerHelpers.ts
+++ b/sdk/ai/ai-projects/src/restorePollerHelpers.ts
@@ -2,7 +2,10 @@
 // Licensed under the MIT License.
 
 import { AIProjectClient } from "./aiProjectClient.js";
-import { _updateMemoriesDeserialize } from "./api/memoryStores/operations.js";
+import {
+  createMemoryStoreUpdateMemoriesPoller,
+  MemoryStoreUpdateMemoriesPoller,
+} from "./api/memoryStores/memoryStoreUpdateMemoriesPoller.js";
 import { getLongRunningPoller } from "./static-helpers/pollingHelpers.js";
 import { OperationOptions, PathUncheckedResponse } from "@azure-rest/core-client";
 import { AbortSignalLike } from "@azure/abort-controller";
@@ -51,9 +54,21 @@ export function restorePoller<TResponse extends PathUncheckedResponse, TResult>(
   const resourceLocationConfig = metadata?.["resourceLocationConfig"] as
     | ResourceLocationConfig
     | undefined;
-  const { deserializer, expectedStatuses = [] } =
-    getDeserializationHelper(initialRequestUrl, requestMethod) ?? {};
-  const deserializeHelper = options?.processResponseBody ?? deserializer;
+  const helper = getDeserializationHelper(initialRequestUrl, requestMethod);
+  if (helper?.kind === "memoryUpdate") {
+    return createMemoryStoreUpdateMemoriesPoller(
+      (client as any)["_client"] ?? client,
+      helper.expectedStatuses ?? ["202", "200"],
+      undefined,
+      {
+        updateIntervalInMs: options?.updateIntervalInMs,
+        abortSignal: options?.abortSignal,
+        restoreFrom: serializedState,
+      },
+    ) as MemoryStoreUpdateMemoriesPoller as PollerLike<OperationState<TResult>, TResult>;
+  }
+  const deserializeHelper = options?.processResponseBody ?? helper?.deserializer;
+  const expectedStatuses = helper?.expectedStatuses ?? [];
   if (!deserializeHelper) {
     throw new Error(
       `Please ensure the operation is in this client! We can't find its deserializeHelper for ${sourceOperation?.name}.`,
@@ -75,13 +90,14 @@ export function restorePoller<TResponse extends PathUncheckedResponse, TResult>(
 
 interface DeserializationHelper {
   // eslint-disable-next-line @typescript-eslint/no-unsafe-function-type
-  deserializer: Function;
-  expectedStatuses: string[];
+  deserializer?: Function;
+  expectedStatuses?: string[];
+  kind?: "memoryUpdate";
 }
 
 const deserializeMap: Record<string, DeserializationHelper> = {
   "POST /memory_stores/{name}:update_memories": {
-    deserializer: _updateMemoriesDeserialize,
+    kind: "memoryUpdate",
     expectedStatuses: ["202", "200"],
   },
 };