Quickstart-Alibaba Cloud Model Studio(Model Studio)-阿里云帮助中心

Write, view, and search memories in 3 steps

Use the default memory to write, view, and search memories in 3 steps. To customize memory rules, see Create memory.

Prerequisites

First-time use requires activating Memory: open the Memory page in the Bailian console and click Activate Now
DASHSCOPE_API_KEY configured. See Get API key
For Python SDK: pip install agentscope-runtime

Step 1: Write memory

Call AddMemory to pass a conversation to the memory. The system auto-extracts factual memories.

cURL

curl -X POST https://dashscope.aliyuncs.com/api/v2/apps/memory/add \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "messages": [
      {"role": "user", "content": "Remind me to drink water at 9 AM every day"},
      {"role": "assistant", "content": "Got it, recorded"},
      {"role": "user", "content": "Remind me to organize meeting notes at 10 AM tomorrow"}
    ],
    "user_id": "user_001"
  }'

Python

from agentscope_runtime.tools.modelstudio_memory import (
    AddMemory, AddMemoryInput, Message,
)
import asyncio

async def add_memory_example():
    add_memory = AddMemory()
    try:
        await add_memory.arun(AddMemoryInput(
            user_id="user_001",
            messages=[
                Message(role="user", content="Remind me to drink water at 9 AM every day"),
                Message(role="assistant", content="Got it, recorded"),
                Message(role="user", content="Remind me to organize meeting notes at 10 AM tomorrow"),
            ]
        ))
        print("Memory written")
    finally:
        await add_memory.close()

asyncio.run(add_memory_example())

Step 2: View memory

In the Bailian console, open the default memory's Memory details tab. Enter memory entity ID user_001 and click View to see auto-extracted factual memories.

Or list memories via API:

cURL

curl -X GET "https://dashscope.aliyuncs.com/api/v2/apps/memory/memory_nodes?user_id=user_001&page_size=10&page_num=1" \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --header "Content-Type: application/json"

Python

from agentscope_runtime.tools.modelstudio_memory import (
    ListMemory, ListMemoryInput,
)
import asyncio

async def list_memory_example():
    list_memory = ListMemory()
    try:
        result = await list_memory.arun(ListMemoryInput(
            user_id="user_001",
            page_size=10,
            page_num=1
        ))
        for node in result.memory_nodes:
            print(f"Memory: {node.content}")
    finally:
        await list_memory.close()

asyncio.run(list_memory_example())

Step 3: Search memory

In the console, switch to the Memory search tab. Enter entity ID user_001, type "What do I need to do?" in the input, and click Run.

Or search via API:

cURL

curl -X POST https://dashscope.aliyuncs.com/api/v2/apps/memory/memory_nodes/search \
  --header "Authorization: Bearer $DASHSCOPE_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "user_id": "user_001",
    "messages": [{"role": "user", "content": "What do I need to do?"}],
    "top_k": 10,
    "min_score": 0.3,
    "plan_version": "Lite"
  }'

Python

from agentscope_runtime.tools.modelstudio_memory import (
    SearchMemory, SearchMemoryInput, Message,
)
import asyncio

async def search_memory_example():
    search_memory = SearchMemory()
    try:
        result = await search_memory.arun(SearchMemoryInput(
            user_id="user_001",
            messages=[Message(role="user", content="What do I need to do?")]
        ))
        for node in result.memory_nodes:
            print(f"Memory: {node.content}")
    finally:
        await search_memory.close()

asyncio.run(search_memory_example())

NoteYou've completed writing, viewing, and searching memories. Inject the results into your prompt for personalized responses.

ImportantAfter the core flow, continue to create a memory with custom rules.