agentleFS
Google CloudKnown publisherGoogleCloudPlatform/devrel-demos/ai-ml/dev-signal/.agent/skills/adk-memory-bank-initializer/SKILL.md

adk-memory-bank-initializer

Skill397 starsChanged 12 days agoApache-2.0View on GitHub

Helps developers implement the long-term memory layer by providing the boilerplate code for the VertexAiMemoryBankService and the save_session_to_memory_callback.

The file

Files
SKILL.md

adk-memory-bank-initializer

This skill helps you integrate long-term persistence into your AI agent using the Vertex AI Memory Bank. It ensures your agent "remembers" user preferences across sessions.

Usage

Ask Antigravity to:

  • "Initialize the memory bank for my agent"
  • "Add a persistence callback to my root agent"
  • "Set up VertexAiMemoryBankService"

Memory Integration Pattern

The integration involves:

  1. Service Initialization: Setting up the VertexAiMemoryBankService with the correct project and location.
  2. Persistence Callback: Implementing a defensive save_session_to_memory_callback that runs after every turn.
  3. Agent Configuration: Passing the memory_service to the Runner or App.
  4. Tool Selection: Using LoadMemoryTool and PreloadMemoryTool to manage context recall.

Python Boilerplate

Refer to the included scripts/memory_config.py for the standard implementation pattern.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.