Deconstructing the AI Framework: From Intelligent Agents to Decentralization Exploration

Preface

Recently, the narrative of the combination of AI and cryptocurrency has developed rapidly. Market attention has shifted to technology-driven "framework-type" projects, which have generated multiple projects with market values exceeding one hundred million and even one billion in a short period. These projects have derived a new asset issuance model: issuing tokens based on GitHub code repositories, and Agents built on frameworks can also issue tokens again. This model is based on frameworks, with Agents as the application layer, forming a unique infrastructure model of the AI era. This article will explore the impact of AI frameworks on the cryptocurrency field.

I. Framework Overview

AI frameworks are underlying development tools or platforms that integrate pre-built modules, libraries, and tools to simplify the process of building complex AI models. It can be understood as the operating system of the AI era, similar to Windows and Linux in desktop systems or iOS and Android in mobile devices. Each framework has its own characteristics, and developers can choose based on their needs.

Although the "AI framework" is a new concept in the cryptocurrency field, its development has a history of nearly 14 years. There are mature frameworks available in the traditional AI field, such as TensorFlow and Pytorch. The framework projects that have emerged in cryptocurrency are designed to meet the needs of a large number of agents and to expand into other fields, forming AI frameworks in different subfields.

1.1 Eliza

Eliza is a multi-Agent simulation framework for creating, deploying, and managing autonomous AI Agents. It is developed in TypeScript and has good compatibility and API integration capabilities. Eliza is primarily aimed at social media scenarios, supporting multi-platform integration and various media content processing.

Use cases supported by Eliza include AI assistant applications, social media characters, knowledge workers, and interactive roles. It supports local inference of open-source models and cloud inference, with the default configuration being Nous Hermes Llama 3.1B, and is integrated with Claude to handle complex queries.

1.2 G.A.M.E

G.A.M.E is an automated multi-modal AI framework for generation and management, primarily used for intelligent NPC design in games. Its feature allows users with low-code or even no-code background to participate in Agent design.

The core design of G.A.M.E is a modular design that works through the collaboration of multiple subsystems, including the Agent prompt interface, perception subsystem, strategic planning engine, world context, dialogue processing module, etc. This framework mainly focuses on the decision-making, feedback, perception, and personality of the Agent in virtual environments, suitable for gaming and metaverse scenarios.

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 interface for easy interaction with multiple LLM service providers and vector databases.

The core features of Rig include a unified interface, modular architecture, type safety, and efficient performance. It is suitable for building problem-solving systems, document search tools, chatbots, and content creation scenarios.

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 inherits the core features of the Zerebro project but adopts a more modular and extensible design.

ZerePy provides a command-line interface that supports large language models from OpenAI and Anthropic, integrates X platform API, and plans to add a memory system in the future. Compared to Eliza, ZerePy focuses more on simplifying the process of deploying AI Agents on specific social platforms.

2. Comparison of Development Paths

The development path of AI Agents has similarities with the recent BTC ecosystem. The development of the BTC ecosystem can be summarized as: BRC20 - multi-protocol competition - BTC L2 - BTCFi. AI Agents have undergone the development process of GOAT/ACT - social agents/analytical AI agents - framework competition. In the future, there may be infrastructure projects focused on the decentralization and security of agents.

Unlike the BTC ecosystem, the AI Agent narrative does not replicate the history of smart contract chains. Existing AI framework projects provide new infrastructure development ideas. Compared to Memecoin Launchpad and inscription protocols, the AI framework is more similar to future public chains, while the Agent is more akin to future Dapps.

3. The Significance of Blockchain Integration

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

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

2. Provide blockchain-based security solutions, especially for Agents that can interact with real or virtual wallets.

3. Create unique blockchain financial gameplay, such as new automatic market-making or investment mechanisms based on Agents.

4. Achieve a transparent and traceable reasoning process to enhance interoperability.

4. The Prospects of the Creative Economy

Framework projects may provide entrepreneurial opportunities similar to the GPT Store in the future. Simplifying the agent construction process and offering a framework for complex functionality combinations may have more advantages, forming a more interesting Web3 creative economy than the GPT Store.

Compared to the GPT Store, the Agent creative economy in the Web3 environment may be fairer and introduce a community economy to enhance Agents. This will provide opportunities for ordinary people to participate, and future AI Memes might be smarter and more interesting than the existing ones.