ADK memory example

This example demonstrates how to use the ADK's InMemoryMemoryService to manage long-term conversational memory across different sessions. It shows how an agent can capture information in one session and another agent can recall it in a subsequent session using a memory retrieval tool.

Requirements

• Python 3.10+
• A Google API key set as an environment variable (GOOGLE_API_KEY)

Steps for running this example in the shell

1. Install dependencies:

python -m venv .venv

# macOS/Linux:
source .venv/bin/activate

# Windows Command Prompt:
.venv\Scripts\activate.bat

# Windows PowerShell:
.venv\Scripts\Activate.ps1

pip install -r requirements.txt

2. Export your API key as an environment variable:

export GOOGLE_API_KEY="sk-..." # Windows cmd: set GOOGLE_API_KEY="sk-..." # Windows PowerShell: $env:GOOGLE_API_KEY="sk-..."

3. Run the script:

python memory_example.py

Output

The script will execute two distinct scenarios:

• Turn 1: An InfoCaptureAgent will acknowledge a user's statement, and the session's content will be added to the InMemoryMemoryService.
• Turn 2: A MemoryRecallAgent (equipped with a load_memory tool) will be queried. It should recall the information captured in Turn 1 from the memory service.