Skip to main content
πŸ“’ 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.
πŸŽ‰ We’re excited to announce that Claude 4 is now available with Zentry! Check it out here.
Zentry offers two powerful ways to leverage our technology: our managed platform and our open source solution. Check out our Playground to see Zentry in action.

Zentry Platform (Managed Solution)

Our fully managed platform provides a hassle-free way to integrate Zentry’s capabilities into your AI agents and assistants. Sign up for Zentry platform here. The Zentry SDK supports both Python and JavaScript, with full TypeScript support as well. Follow the steps below to get started with Zentry Platform:
  1. Install Zentry
  2. Add Memories
  3. Retrieve Memories

1. Install Zentry

pip install zentry
  1. Sign in to Zentry Platform
  2. Copy your API Key from the dashboard
Get API Key from Zentry Platform

2. Add Memories

import os
from zentry import MemoryClient

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

client = MemoryClient()
messages = [
    {"role": "user", "content": "Thinking of making a sandwich. What do you recommend?"},
    {"role": "assistant", "content": "How about adding some cheese for extra flavor?"},
    {"role": "user", "content": "Actually, I don't like cheese."},
    {"role": "assistant", "content": "I'll remember that you don't like cheese for future recommendations."}
]
client.add(messages, user_id="alex")

3. Retrieve Memories

# Example showing location and preference-aware recommendations
query = "I'm craving some pizza. Any recommendations?"
filters = {
    "AND": [
        {
            "user_id": "alex"
        }
    ]
}
client.search(query, version="v2", filters=filters)
filters = {
   "AND": [
      {
         "user_id": "alex"
      }
   ]
}

all_memories = client.get_all(version="v2", filters=filters, page=1, page_size=50)

Zentry Platform

Learn more about Zentry platform

Zentry Open Source

Our open-source version is available for those who prefer full control and customization. You can self-host Zentry on your infrastructure and integrate it with your AI agents and assistants. Checkout our GitHub repository Follow the steps below to get started with Zentry Open Source:
  1. Install Zentry Open Source
  2. Add Memories
  3. Retrieve Memories

1. Install Zentry Open Source

pip install zentry

2. Add Memories

from zentry import Memory
m = Memory()
# For a user
result = m.add("I like to drink coffee in the morning and go for a walk.", user_id="alice", metadata={"category": "preferences"})

3. Retrieve Memories

related_memories = m.search("Should I drink coffee or tea?", user_id="alice")