Google ADK + MemorySync

Overview

Install google-adk-memorysync and pass MemorySyncMemoryService() to Runner(memory_service=...): all four BaseMemoryService methods are real — add_session_to_memory sends every message the user wrote to fact extraction (and raises on failure), search_memory powers ADK’s native load_memory and preload_memory tools. A context tool guarantees per-turn injection and sends the user’s message, an after_model_callback sends the invocation’s user message once the model has answered, and five structured tools give agents explicit memory. Only the durable facts are stored; the agent’s replies are not sent. The only vendor ADK integration whose ingestion is not a no-op.

Setup status and requirements

Supported version

google-adk-memorysync 1.1.0 (PyPI)

Last setup review

2026-10-01

Permissions

A MemorySync API key with read and write scopes; the delete tool needs delete permission.

Limits

Requires google-adk 2.0+ (Python 3.10+). Python only — TypeScript agents use the Vercel AI SDK or Mastra integrations.

Capabilities

• All four BaseMemoryService methods implemented — ingestion included
• Powers ADK’s native load_memory and preload_memory tools unchanged
• Re-ingesting a session is recognised via event-id seeds — nothing extracted twice
• Context tool: guaranteed injection, deduped per invocation
• after_model_callback sends the user’s message once per invocation
• Cross-app user memory by default; scope_to_app=True to silo
• Five never-raise agent tools with a read-only mode

Quick Start

from google.adk.agents import LlmAgent
from google.adk.runners import Runner
from google.adk.tools import preload_memory
from google_adk_memorysync import MemorySyncMemoryService

memory_service = MemorySyncMemoryService()

agent = LlmAgent(
    name="assistant",
    model="your-model",
    instruction="You are a helpful assistant.",
    tools=[preload_memory],
)
runner = Runner(agent=agent, app_name="support",
                session_service=session_service,
                memory_service=memory_service)

Use Cases

Explore More