Deconstructing AI Frameworks: From Intelligent Agents to Decentralization Exploration

Preface

Recently, the narrative of the combination of AI and cryptocurrency has developed rapidly, with market attention gradually shifting towards technology-driven "framework-type" projects. This niche sector has seen the emergence of several star projects with market capitalizations exceeding hundreds of millions and even billions within just a few weeks. These types of projects have also given rise to a new asset issuance model - issuing tokens based on GitHub repositories, while smart agents developed on the framework can also issue tokens again. Based on the framework and with smart agents as applications, a unique infrastructure model for the AI era has been formed. This article will start from the concept of frameworks to explore the significance of AI frameworks for the cryptocurrency industry.

1. Framework Overview

AI frameworks are a type of underlying development tool or platform that integrates pre-built modules, libraries, and tools to simplify the process of building complex AI models. They can be compared to operating systems in the AI era. Although "AI frameworks" is an emerging concept in the cryptocurrency field, its development history is nearly 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 the cryptocurrency industry mainly target the demand for intelligent agents brought about by the AI boom and extend to other fields. Here are a few examples of mainstream frameworks:

1.1 Eliza

Eliza is a multi-intelligent agent simulation framework focused on creating, deploying, and managing autonomous AI agents. Developed in TypeScript, it has good compatibility and API integration capabilities. It is mainly applied in social media scenarios, supporting multi-platform integration and various media content processing.

Use cases supported by Eliza include: AI assistant applications, social media roles, knowledge workers, and interactive roles. Supported models include local inference with open source models, OpenAI API cloud inference, and more.

1.2 G.A.M.E

G.A.M.E(Generative Autonomous Multimodal Entities Framework) is an automatically generated and managed multimodal AI framework, primarily designed for intelligent NPCs in games. It features support for low-code and even no-code operations.

G.A.M.E adopts a modular design, including multiple subsystems such as the Agent prompt interface, perception subsystem, strategic planning engine, world context, and dialogue processing module. Besides gaming, this framework is also applicable to metaverse applications.

1.3 Rig

Rig is an open-source tool written in Rust, designed to simplify the development of large language model applications. It provides a unified interface that supports 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 question and answer systems, document search tools, and context-aware chatbots, among others.

1.4 ZerePy

ZerePy is an open-source framework based on Python, focused on simplifying the process of deploying and managing AI agents on the X platform. It provides a command line interface, supports modular design, and can integrate various LLMs and social platform APIs.

Compared to Eliza, ZerePy focuses more on the deployment of AI agents on specific social platforms rather than multi-agent simulations and broad AI research.

2. Similarities with the BTC Ecosystem

The development path of AI agents has similarities with the recent BTC ecosystem. The BTC ecosystem has gone through the BRC20, multi-protocol competition, BTC L2, and the BTCFi phase centered around Babylon. AI agents have experienced the GOAT/ACT and the competition phase of social agents/analytical AI agent frameworks. In the future, it may revolve around the decentralization and security of agents.

However, AI agent narratives do not reproduce the history of smart contract chains. Existing AI framework projects provide new ideas for infrastructure development. Compared to Memecoin launchpads and inscription protocols, AI frameworks are more akin to future public chains, while agents are similar to future Dapps.

3. The Significance of On-Chain

The core issue facing the combination of blockchain and AI is: Is it meaningful? Referring to the successful experiences of DeFi, the reasons supporting agent chainization may include:

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

2. Provide blockchain-based security solutions to meet the needs for interaction between agents and real or virtual wallets.

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

4. Achieve transparent and traceable reasoning, enhance interoperability, making it more attractive compared to proxy 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 feature combinations could hold an advantage, creating a more interesting Web3 creative economy than the GPT Store.

Compared to the current model dominated by traditional Web2 companies, the Web3 agency creative economy will be more open and fair. The introduction of community economics can make agencies more refined, and future AI meme projects may be smarter and more entertaining than the agencies on existing platforms. This will provide opportunities for ordinary people to participate and promote the diversified development of the AI agency ecosystem.