📢 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.

You can create a personalised Eliza OS Character using ZENTRY. This guide will walk you through the necessary steps and provide the complete code to get you started.

​
Overview

ElizaOS is a powerful AI agent framework for autonomy & personality. It is a collection of tools that help you create a personalised AI agent.

​
Setup

You can start by cloning the eliza-os repository:

git clone https://github.com/elizaOS/eliza.git

Change the directory to the eliza-os repository:

cd eliza

Install the dependencies:

pnpm install

Build the project:

pnpm build

​
Setup ENVs

Create a .env file in the root of the project and add the following ( You can use the .env.example file as a reference):

# ZENTRY Configuration
ZENTRY_API_KEY= # ZENTRY API Key ( Get from https://app.zentry.gg/dashboard/api-keys )
ZENTRY_USER_ID= # Default: eliza-os-user
ZENTRY_PROVIDER= # Default: openai
ZENTRY_PROVIDER_API_KEY= # API Key for the provider (openai, anthropic, etc.)
SMALL_ZENTRY_MODEL= # Default: gpt-4o-mini
MEDIUM_ZENTRY_MODEL= # Default: gpt-4o
LARGE_ZENTRY_MODEL= # Default: gpt-4o

​
Make the default character use ZENTRY

By default, there is a character called eliza that uses the ollama model. You can make this character use ZENTRY by changing the config in the agent/src/defaultCharacter.ts file.

modelProvider: ModelProviderName.ZENTRY,

This will make the character use ZENTRY to generate responses.

​
Run the project

pnpm start

​
Conclusion

You have now created a personalised Eliza OS Character using ZENTRY. You can now start interacting with the character by running the project and talking to the character.

This is a simple example of how to use ZENTRY to create a personalised AI agent. You can use this as a starting point to create your own AI agent.