Skip to main content
📢 Announcing our research paper: Zentry achieves 26% higher accuracy than OpenAI Memory, 91% lower latency, and 90% token savings! Read the paper to learn how we're revolutionizing AI agent memory.

​
Benefits of Memory Customization

Memory customization offers several key benefits: • Focused Storage: Store only relevant information for a streamlined system. • Improved Accuracy: Curate memories for more accurate and relevant retrieval. • Enhanced Privacy: Exclude sensitive information for better privacy control. • Resource Efficiency: Optimize storage and processing by keeping only pertinent data. • Personalization: Tailor the experience to individual user preferences. • Contextual Relevance: Improve effectiveness in specialized domains or applications. These benefits allow users to fine-tune their memory systems, creating a more powerful and personalized AI assistant experience.

​
Memory Inclusion

Users can define specific kinds of memories to store. This feature enhances memory management by focusing on relevant information, resulting in a more efficient and personalized experience. Here’s how you can do it: 
import os
from Zentry import MemoryClient

os.environ["Zentry_API_KEY"] = "your-api-key"

m = MemoryClient()

# Define what to include
includes = "sports related things"

messages = [
    {"role": "user", "content": "Hi, my name is Alice and I love to play badminton"},
    {"role": "assistant", "content": "Nice to meet you, Alice! Badminton is a great sport."},
    {"role": "user", "content": "I love music festivals"},
    {"role": "assistant", "content": "Music festivals are exciting! Do you have a favorite one?"},
    {"role": "user", "content": "I love eating spicy food"},
    {"role": "assistant", "content": "Spicy food is delicious! What's your favorite spicy dish?"},
    {"role": "user", "content": "I love playing baseball with my friends"},
    {"role": "assistant", "content": "Baseball with friends sounds fun!"},
]

client.add(messages, user_id="alice", includes=includes)

​
Memory Exclusion

In addition to specifying what to include, users can also define exclusion rules for their memory management. This feature allows for fine-tuning the memory system by instructing it to omit certain types of information. Here’s how you can do it: 
from Zentry import MemoryClient

m = MemoryClient(api_key="xxx")

# Define what to exclude
excludes = "food preferences"

messages = [
    {"role": "user", "content": "Hi, my name is Alice and I love to play badminton"},
    {"role": "assistant", "content": "Nice to meet you, Alice! Badminton is a great sport."},
    {"role": "user", "content": "I love music festivals"},
    {"role": "assistant", "content": "Music festivals are exciting! Do you have a favorite one?"},
    {"role": "user", "content": "I love eating spicy food"},
    {"role": "assistant", "content": "Spicy food is delicious! What's your favorite spicy dish?"},
    {"role": "user", "content": "I love playing baseball with my friends"},
    {"role": "assistant", "content": "Baseball with friends sounds fun!"},
]

client.add(messages, user_id="alice", excludes=excludes)
If you have any questions, please feel free to reach out to us using one of the following methods:

Telegram

Join our community

GitHub

Ask questions on GitHub

Support

Talk to founders