Memory - ChatATP Studio Documentation

Use client.memories for Agent memory and per-user memory.

Create and list Agent memory

from chatatp_studio import ChatATPClient

async with ChatATPClient(api_key="chatatp_sk_...") as client:
    memory = await client.memories.create(
        7,
        title="Preferred response style",
        content="The user prefers concise answers.",
        memory_type="preference",
        importance=1.0,
    )
    memories = await client.memories.list(7)

Memory indexing is asynchronous. Inspect each memory’s status, chunk_count, and error_message.

Per-user memory and search

await client.memories.create(
    7,
    title="Subscription plan",
    content="The user is on the Pro plan.",
    agent_user_id=42,
    memory_type="fact",
)

result = await client.memories.search(
    7,
    42,
    "What plan is the user on?",
    top_k=5,
)
print(result["context"], result["has_context"])

For the equivalent Studio CLI workflow, see the Memory section in the CLI overview.