Long-Term Knowledge Storage and Retrieval › Storing Information for Later
Michael BrenndoerferJuly 3, 20251 min read
AI Agent HandbookAll chapters Part 6 of 15Memory and Retrieval - How Agents Remember
Long-Term Knowledge Storage and Retrieval › Storing Information for LaterOne section · Sections in this chapter3 / 13 ↓
Sections in this chapter13
Reading tools Definitions & inline links
Toggle tooltip visibility. Hover over underlined terms for instant definitions.
Article links
Make inline references clickable
The simplest form of long-term memory is a key-value store. You save information with a label (the key) and retrieve it later using that same label.
Here's a basic example using a Python dictionary that persists to a file:
In[3]:
Codeimport json
import os
class SimpleMemory:
def __init__(self, memory_file="assistant_memory.json"):
self.memory_file = memory_file
self.memory = self._load_memory()
def _load_memory(self):
"""Load memory from file if it exists"""
if os.path.exists(self.memory_file):
with open(self.memory_file, "r") as f:
return json.load(f)
return {}
def _save_memory(self):
"""Save memory to file"""
with open(self.memory_file, "w") as f:
json.dump(self.memory, f, indent=2)
def store(self, key, value):
"""Store a fact in long-term memory"""
self.memory[key] = value
self._save_memory()
return f"Remembered: {key}"
def retrieve(self, key):
"""Retrieve a fact from long-term memory"""
return self.memory.get(key, "I don't have that information stored.")
## Example usage
memory = SimpleMemory()
memory.store("user_birthday", "July 20")
memory.store("favorite_restaurant", "Luigi's Italian Kitchen")
## Later, even after restarting the program
print(memory.retrieve("user_birthday")) # Output: July 20Out[3]:
ConsoleJuly 20
This works, but it has a limitation: you need to know the exact key to retrieve information. What if you want to ask, "What do you know about my food preferences?" The assistant would need to search through all stored information to find relevant facts.