Deconstructing the AI Framework: From Intelligent Agents to Decentralization Exploration

Introduction

Recently, the narrative of the combination of AI and cryptocurrency has developed rapidly. Market attention has shifted to technology-driven "framework-type" projects, with several new stars emerging in just a few weeks, each with a market capitalization exceeding one billion or even ten billion. These projects have given rise to new asset issuance models: issuing tokens from Github code repositories, and Agents built on frameworks can issue tokens again. With frameworks as the foundation and Agents on top, a unique infrastructure model for the AI era is formed. This article will explore the impact of AI frameworks on the cryptocurrency sector.

1. Introduction to the Framework

AI frameworks are fundamental development tools or platforms that integrate pre-built modules, libraries, and tools, simplifying the process of building complex AI models. They can be understood as operating systems of the AI era, such as Windows, Linux, iOS, or Android. Each framework has its own advantages and disadvantages, allowing developers to choose according to their needs.

Although the "AI framework" is a new concept in the cryptocurrency field, the development of AI frameworks has a history of nearly 14 years. There are mature frameworks available in the traditional AI field, such as TensorFlow and Pytorch. The emerging framework projects in cryptocurrency are designed to meet the demand for agents under the AI boom and are expanding into other areas. Here are a few mainstream frameworks:

1.1 Eliza

Eliza is a multi-Agent simulation framework for creating, deploying, and managing autonomous AI Agents. Developed in TypeScript, it has good compatibility and is easy to integrate with APIs. It is mainly aimed at social media scenarios, supporting multi-platform integration and media content processing.

Supported use cases include:

• AI assistant applications
• Social Media Role
• Knowledge Workers
• Interactive Role

Supported models include open-source model local inference, OpenAI API cloud inference, etc.

1.2 G.A.M.E

G.A.M.E is a multimodal AI framework for automatic generation and management launched by Virtual, mainly designed for intelligent NPCs in games. It features low-code or even no-code usability for users.

The core design is a modular design that works through the collaboration of multiple subsystems, including the Agent prompt interface, perception subsystem, strategic planning engine, and other modules.

Applicable to gaming and metaverse scenarios, multiple projects have adopted this framework for development.

1.3 Rig

Rig is an open-source tool written in Rust, designed to simplify the development of applications using large language models. It provides a unified operating interface, facilitating interaction with multiple LLM service providers and vector databases.

Core Features:

• Unified Interface
• Modular Architecture
• Type Safety
• High Efficiency

Applicable for building Q&A systems, document search tools, chatbots, etc.

1.4 ZerePy

ZerePy is an open-source framework based on Python that simplifies the process of deploying and managing AI Agents on the X platform. It provides a command-line interface and supports modular design.

Main functions:

• LLM Integration
• X Platform Integration
• Modular Connection System
• Memory system ( planning )

Focus on simplifying the process of deploying AI Agents on the X platform.

2. Development Path Analysis

The development path of AI Agents is similar to the recent BTC ecosystem. It can be summarized as: GOAT/ACT - Social-type Agents/Analytical AI Agents - Framework competition. In the future, infrastructure projects focusing on Agent Decentralization and security may become the main theme.

Unlike the BTC ecosystem, the AI Agent narrative does not replicate the history of smart contract chains. Existing AI framework projects offer new infrastructure development ideas. The AI framework is more like a future public chain, while the Agent is more like a future Dapp.

In the future, the competition may shift from EVM and heterogeneous chains to framework competition. The key issue is how to achieve Decentralization or chainification, as well as the significance of development on the blockchain.

III. The Significance of On-Chain

The combination of AI and blockchain needs to consider its significance. Possible meanings include:

1. Lower usage costs, increase accessibility and choice, allowing ordinary users to participate in AI "rental rights".

2. Provide blockchain-based security solutions to meet the needs of Agent and real-world interaction.

3. Implement unique blockchain financial models, such as new AMM or investment mechanisms based on Agents.

4. Achieve better interoperability through transparent and traceable reasoning.

4. Prospects of the Creative Economy

Framework projects may provide entrepreneurial opportunities similar to the GPT Store in the future. Frameworks that simplify the Agent construction process could have an advantage, creating a more interesting Web3 creative economy than the GPT Store.

Compared to the current GPT Store, the Web3 Agent creative economy may be fairer, allowing ordinary people to participate. Future AI Memes might be smarter and more interesting than the Agents on existing platforms.