Memory for Strands Agents agents

• Which value is current. Harny keeps dated memory, so a changed value with a newer timestamp becomes the current value and the earlier value stays answerable by date.
• When a fact happened. Harny stores each memory with an occurred-at time, so you can ask what was true on a given day.
• One person across sources. Harny keeps one private memory per person, and connected accounts add their data to that memory.

Each function is wrapped with the tool decorator and given to the agent. The tools call the Memory API with the app key from your server, so the agent can read and write a person's memory through them.

The user id comes from your own sign-in, and the agent passes only the content it needs.

import os
import requests

BASE = "https://api.harny.ai/v1/memory"

def make_memory_tools(user_id: str):
    headers = {
        "Authorization": f"Bearer {os.environ['HARNY_APP_KEY']}",
        "X-Harny-User": user_id,  # set by your application, never by the model
    }

    def recall_memory(question: str) -> str:
        """Look up what is known about this user that is relevant to a question."""
        r = requests.post(f"{BASE}/recall", headers=headers,
                          json={"query": question, "identity": user_id})
        return r.text

    def store_memory(text: str, happened_at: str) -> str:
        """Save a fact with the ISO time it happened."""
        r = requests.post(f"{BASE}/ingest", headers=headers,
                          json={"content": text, "timestamp": happened_at})
        return r.text

    return [recall_memory, store_memory]

from strands import Agent, tool

agent = Agent(tools=[tool(f) for f in make_memory_tools(user_id)])
agent("What is the Acme pilot budget?")

Memory results with dated sources and source labels. Results carry sources with sourceId, occurredAt and label.

• POST https://api.harny.ai/v1/memory/ingest takes id, content, label and timestamp.
• POST https://api.harny.ai/v1/memory/recall takes query and identity, and returns results with sources.

Example: your agent asks “what is the Acme pilot budget?” and gets this back. Your code hands the model the content and the source label, so it can say who said it and when.

{
  "asOf": "2026-07-29T00:00:00Z",
  "results": [
    {
      "rank": 1,
      "occurredAt": "2026-07-28T16:00:00Z",
      "content": "Acme pilot budget: currently 40k.",
      "sources": [
        { "sourceId": "call-8821", "label": "Email from Nadia" }
      ]
    }
  ]
}

• Use the framework's own session state for the conversation in progress, such as the messages and the steps of the current task.
• Add Harny when a person's facts need to last across sessions, change over time, or be answered as of a date.