Memory for Agno agents

• Which value is current. Harny keeps dated memories. 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 date.
• One person across sources. Each person's memory is separate in Harny, and recall returns each result with its sources.

Plain functions in the tools list become tools the agent can call. You can write functions that call the Harny Memory API from your server to read and write memory, so the agent works with memory as it works with any other tool.

Take the user id from your own sign-in and send it in the X-Harny-User header, so the id does not depend on the model's output.

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 agno.agent import Agent

agent = Agent(
    model=model,  # the model you already use in Agno
    tools=make_memory_tools(user_id),
    instructions="Call recall_memory before you answer a question about a customer.",
)
agent.print_response("What is the Acme pilot budget?")

Memory results with sources. Each result carries its sources, with a source id, the date it happened and a label.

• POST https://api.harny.ai/v1/memory/ingest takes id, content, label and timestamp. It answers 202 with an ingestionId.
• 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 Agno's own session state for the conversation in progress, such as the messages and tool results of the current run.
• Add Harny when a person's facts need to last across sessions, change over time, or be answered as of a date.