Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Eliza: A Web3 friendly AI Agent Operating System

Shaw Walters, Sam Gao, Shakker Nerd, Feng Da, Warren Williams, Ting-Chien Meng, Amie Chow, Hunter Han, Frank He, Allen Zhang, Ming Wu, Timothy Shen, Maxwell Hu, Jerry Yan

TL;DR

Eliza addresses the gap between AI agents and Web3 by introducing an open-source, TypeScript-based AI agent operating system (ElizaOS) that natively integrates blockchain data and smart contracts. The framework centers on core concepts (Agents, Character Files, Providers, Actions, Evaluators) and a robust intent-recognition pipeline, wrapped in a pluggable plugin architecture with media, Web3, and infrastructure plugins. Benchmark results (GAIA) show Eliza achieving competitive general-agent performance with multi-agent swarms, while a Web3 benchmark outlines a practical, safety-conscious Turing-like evaluation for Web3 tasks. The work demonstrates tangible use cases (e.g., Solana integration and image generation workflows) and argues for broad potential adoption through modularity, extensibility, and community-driven development.

Abstract

AI Agent, powered by large language models (LLMs) as its cognitive core, is an intelligent agentic system capable of autonomously controlling and determining the execution paths under user's instructions. With the burst of capabilities of LLMs and various plugins, such as RAG, text-to-image/video/3D, etc., the potential of AI Agents has been vastly expanded, with their capabilities growing stronger by the day. However, at the intersection between AI and web3, there is currently no ideal agentic framework that can seamlessly integrate web3 applications into AI agent functionalities. In this paper, we propose Eliza, the first open-source web3-friendly Agentic framework that makes the deployment of web3 applications effortless. We emphasize that every aspect of Eliza is a regular Typescript program under the full control of its user, and it seamlessly integrates with web3 (i.e., reading and writing blockchain data, interacting with smart contracts, etc.). Furthermore, we show how stable performance is achieved through the pragmatic implementation of the key components of Eliza's runtime. Our code is publicly available at https://github.com/ai16z/eliza.

Eliza: A Web3 friendly AI Agent Operating System

TL;DR

Eliza addresses the gap between AI agents and Web3 by introducing an open-source, TypeScript-based AI agent operating system (ElizaOS) that natively integrates blockchain data and smart contracts. The framework centers on core concepts (Agents, Character Files, Providers, Actions, Evaluators) and a robust intent-recognition pipeline, wrapped in a pluggable plugin architecture with media, Web3, and infrastructure plugins. Benchmark results (GAIA) show Eliza achieving competitive general-agent performance with multi-agent swarms, while a Web3 benchmark outlines a practical, safety-conscious Turing-like evaluation for Web3 tasks. The work demonstrates tangible use cases (e.g., Solana integration and image generation workflows) and argues for broad potential adoption through modularity, extensibility, and community-driven development.

Abstract

AI Agent, powered by large language models (LLMs) as its cognitive core, is an intelligent agentic system capable of autonomously controlling and determining the execution paths under user's instructions. With the burst of capabilities of LLMs and various plugins, such as RAG, text-to-image/video/3D, etc., the potential of AI Agents has been vastly expanded, with their capabilities growing stronger by the day. However, at the intersection between AI and web3, there is currently no ideal agentic framework that can seamlessly integrate web3 applications into AI agent functionalities. In this paper, we propose Eliza, the first open-source web3-friendly Agentic framework that makes the deployment of web3 applications effortless. We emphasize that every aspect of Eliza is a regular Typescript program under the full control of its user, and it seamlessly integrates with web3 (i.e., reading and writing blockchain data, interacting with smart contracts, etc.). Furthermore, we show how stable performance is achieved through the pragmatic implementation of the key components of Eliza's runtime. Our code is publicly available at https://github.com/ai16z/eliza.
Paper Structure (47 sections, 4 equations, 5 figures, 2 tables)

This paper contains 47 sections, 4 equations, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Design Principles
  4. Related Works
  5. Plugins
  6. Frameworks
  7. ElizaOS
  8. Core Concepts
  9. Agents
  10. Character Files
  11. Providers
  12. Actions
  13. Evaluators
  14. Intent Recognition
  15. Plugins
  16. ...and 32 more sections

Figures (5)

  • Figure 1: Eliza is a straightforward yet efficient AI agent operating system, offering a seamless experience for developers to effortlessly launch their first-ever web3-oriented AI Agent.
  • Figure 2: Comparison with AI agent frameworks focuses on web3. Score ranging from 0 (worst) to 10 (best), reflect the views of senior developers come from AI and web3 industry.
  • Figure 3: Intent recognition system of Eliza.
  • Figure 4: Web3 AI Agent 'Turing Test': An AI agent operating within the Web3 ecosystem is considered to have passed the 'Turing Test' if it can successfully manage all tasks categorized as Basic, Intermediate, and Advanced as listed above.
  • Figure 5: As of January 1, 2025, numerous representative web3 projects have built AI agents based on ElizaOS, with their combined market capitalization surpassing $20 billion dollars.