Skip to main content
elizaOS Hero Light

​
What is elizaOS?

elizaOS is an all-in-one, extensible platform for building and deploying AI-powered applications. Whether you’re creating sophisticated chatbots, autonomous agents for business process automation, or intelligent game NPCs, elizaOS provides the tools you need to get started quickly and scale effectively. It combines a modular architecture with a library-first approach, giving you full control over your agents’ development, deployment, and management lifecycle.

​
Why Choose elizaOS?

Model Agnostic

Works with all major AI models including OpenAI, Anthropic, Google Gemini, Grok, and local models via Ollama

Multi-Agent Architecture

Designed from the ground up for creating and orchestrating groups of specialized agents

Rich Connectivity

Out-of-the-box connectors for Discord, Telegram, Twitter, Farcaster, and more

Highly Extensible

Powerful plugin system lets you build custom actions, providers, and evaluators

Document Ingestion (RAG)

Ingest documents and allow agents to retrieve information from your data

Production Ready

Built for real-world applications with database support, memory management, and deployment options

​
Core Capabilities

​
AgentRuntime

The heart of elizaOS is the AgentRuntime - a central orchestrator that manages your agent’s lifecycle, loads plugins, and coordinates all interactions. It provides a unified interface for actions, providers, and evaluators to work together seamlessly.

​
Actions

Actions define specific tasks your agent can perform. Each action includes validation logic to determine when it should trigger, and a handler function to execute the task. elizaOS includes 20+ built-in actions including:
  • SEND_MESSAGE: Send messages to rooms and channels
  • UPDATE_ENTITY: Track and update entity information
  • SEARCH_CONTACTS: Find and manage contacts
  • SETTINGS: Configure agent behavior dynamically
  • ROLES: Manage user permissions and access

​
Providers

Providers supply real-time data and context to your agent. They fetch information from external APIs, databases, and services to keep your agent informed and responsive. Use providers to access:
  • Current time and location data
  • User profile information
  • External API data
  • Custom business logic

​
Evaluators

Evaluators analyze conversations and extract insights to build your agent’s memory and contextual awareness. They help your agent:
  • Understand user intent
  • Extract facts and relationships
  • Reflect on interactions
  • Improve future responses

​
Architecture Overview

elizaOS is organized as a monorepo containing all the packages needed to build, run, and deploy agents: 
/
├── packages/
│   ├── typescript/     # @elizaos/core - AgentRuntime and bootstrap plugin
│   ├── python/         # Python implementation
│   ├── rust/           # Rust implementation (native + WASM)
│   └── elizaos/        # CLI for project scaffolding
├── plugins/            # Official plugins (discord, telegram, openai, etc.)
├── examples/           # Example agents and usage patterns
└── ...

​
Get Started in Minutes

Installation

Set up your development environment with Node.js and bun

Quick Start

Build your first AI agent in under 5 minutes

What You Can Build

Explore use cases from chatbots to autonomous agents

Core Concepts

Learn about the fundamental building blocks

​
Community & Support

Discord

Join our community

GitHub

View the source code

Twitter

Follow for updates
elizaOS is open source and MIT licensed. We welcome contributions from the community!

​
Citation

If you use elizaOS in your research, please cite our paper: 
@article{walters2025eliza,
  title={Eliza: A Web3 friendly AI Agent Operating System},
  author={Walters, Shaw and Gao, Sam and Nerd, Shakker and Da, Feng and Williams, Warren and Meng, Ting-Chien and Han, Hunter and He, Frank and Zhang, Allen and Wu, Ming and others},
  journal={arXiv preprint arXiv:2501.06781},
  year={2025}
}

Build docs developers (and LLMs) love

Get started for freeTalk to us