Deconstructing the AI Framework: From Intelligent Agents to Decentralization Exploration

Preface

Recently, the narrative of the combination of AI and cryptocurrencies has developed rapidly. Market attention has shifted to technology-driven "framework-type" projects, and this sub-sector has seen multiple projects with market capitalizations exceeding one hundred million and even one billion emerge within just a few weeks. These projects have given rise to a new asset issuance model - issuing tokens based on GitHub repositories, with Agents developed on the framework being able to issue tokens again. With the framework as the foundation and Agents on top, a model similar to an asset issuance platform is formed, which is actually revealing the unique infrastructure of the AI era. This article will start with an overview of the framework and explore the significance of AI frameworks in the field of cryptocurrencies.

I. Framework Overview

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

Although the "AI framework" is a new concept in the cryptocurrency field, it has a history of 14 years. There are mature frameworks available in the traditional AI field, such as Google's TensorFlow and Meta's Pytorch. The framework projects emerging in cryptocurrency are built based on the massive demand for Agents under the AI boom and extend to other tracks, forming AI frameworks in different subfields.

1.1 Eliza

Eliza is a multi-Agent simulation framework launched by ai16z for creating, deploying, and managing autonomous AI Agents. Developed in TypeScript, it has good compatibility and is easy to integrate with APIs.

Eliza mainly targets social media scenarios, supporting multi-platform integration, including Discord, Twitter, Telegram, etc. It supports media content processing such as PDF analysis, link extraction, audio and video processing, etc.

The use cases supported by Eliza mainly include: AI assistant applications, social media characters, knowledge workers, and interactive roles. Supported models include local inference of open-source models, OpenAI API cloud inference, etc.

1.2 G.A.M.E

G.A.M.E is a multi-modal AI framework for automatic generation and management launched by Virtual, primarily aimed at the design of intelligent NPCs in games. Its feature is that it can be used by low-code or even no-code users.

The core design of G.A.M.E is a modular design where multiple subsystems work together, including the Agent prompt interface, perception subsystem, strategic planning engine, and several other modules.

From a technical architecture perspective, this framework focuses on the decision-making, feedback, perception, and personality of agents in virtual environments, making it suitable for gaming and metaverse scenarios.

1.3 Rig

Rig is an open-source tool written in Rust that simplifies the development of large language model applications. It provides a unified interface to facilitate interaction with multiple LLM service providers and vector databases.

The features of Rig include: unified interface, modular architecture, type safety, efficient performance, etc. The workflow is that user requests pass through the provider abstraction layer, the core layer for processing, and finally generate a response.

Rig is suitable for building question-and-answer systems, document search tools, intelligent chatbots, and other 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 provides a command line interface and supports modular design.

ZerePy supports OpenAI and Anthropic's LLM, integrates X platform API, allowing the Agent to perform various operations. There are plans to integrate a memory system in the future to enhance the Agent's contextual understanding capabilities.

2. Development Path Analysis

The development path of AI Agents has similarities with the recent BTC ecosystem. The BTC ecosystem has gone through stages such as BRC20, multi-protocol competition, BTC L2, and BTCFi. AI Agents develop faster on a mature technology stack, which can be summarized as: GOAT/ACT - social-type Agents/analytical AI - competition among Agent frameworks.

Future infrastructure projects centered around Agent Decentralization and security may become the theme of the next stage. AI framework projects provide new infrastructure ideas, where the AI framework can be likened to future public chains, and Agent can be likened to future Dapps.

3. Discussion on On-Chain Significance

When blockchain integrates with other fields, it must face the question of what it means. Considering the success factors of DeFi, the significance of Agent chainization can be explored from the following points:

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

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

3. Create unique blockchain financial models, such as Agent-related computing power, data tagging investments, etc.

4. Achieve transparent and traceable reasoning, improve interoperability, and be more attractive than the agent browsers provided by traditional internet giants.

4. Outlook on the Creative Economy

Framework projects may offer entrepreneurial opportunities similar to the GPT Store in the future. Simplifying the Agent construction process and providing a framework for complex functionality combinations may hold an advantage, leading to a Web3 creative economy that is more interesting than the GPT Store.

There are many unmet needs in the Web3 space, and the economic system can make policies fairer. Introducing community economics helps improve Agents. The creative economy of Agents will provide opportunities for ordinary people to participate, and future AI Memes may be smarter and more interesting than the Agents on existing platforms.