Deconstructing the AI Framework: Exploring from Intelligent Agents to Decentralization

Introduction

The narrative combining AI and cryptocurrency is rapidly evolving. Recently, market attention has focused on technology-driven "framework" projects, which have generated several projects with market capitalizations exceeding hundreds of millions or even billions in a short period. These projects have given rise to a new asset issuance model: issuing tokens through GitHub code repositories, with Agents developed based on the framework able to reissue tokens. With the framework as the foundation and Agents on top, a model similar to an asset issuance platform is forming, which is, in fact, a unique infrastructure of the AI era. This article will start from the concept of the framework and interpret the significance of AI frameworks for the cryptocurrency industry, combined with personal reflections.

1. What is a framework?

AI framework is a type of underlying development tool or platform that integrates a set of 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 and Linux in desktop systems, or iOS and Android in mobile devices. Each framework has its own advantages and disadvantages, and developers can choose based on their needs.

Although "AI frameworks" are an emerging concept in the cryptocurrency field, they have a history of nearly 14 years since the birth of Theano in 2010. In the traditional AI field, there are mature frameworks available, such as Google's TensorFlow, Meta's Pytorch, and so on.

The emerging framework projects in the cryptocurrency space are built on the massive demand for Agents driven by the AI boom, and have derived into other tracks, forming AI frameworks in different niche areas. Below is an introduction to several mainstream frameworks:

1.1 Eliza

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

Eliza is mainly aimed at social media scenarios and supports multi-platform integration, such as Discord, X/Twitter, Telegram, etc. In terms of media content processing, it supports functions such as PDF document analysis, link content extraction, audio and video processing, etc.

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

1.2 G.A.M.E

G.A.M.E is an automated multimodal AI framework primarily designed for intelligent NPCs in games. The framework is characterized by its accessibility for low-code or no-code users, who can participate in Agent design by simply modifying parameters.

G.A.M.E adopts a modular design, working collaboratively through multiple subsystems. The core architecture includes components such as the Agent interaction interface, perception subsystem, strategy planning engine, world context, and dialogue processing module.

This framework mainly focuses on the decision-making, feedback, perception, and personality of agents in virtual environments, applicable to gaming and metaverse scenarios.

1.3 Rig

Rig is an open-source tool written in Rust, designed to simplify the development of large language model ( LLM ) applications. It provides a unified operating interface, making it easier to interact with multiple LLM service providers and vector databases.

The core features of Rig include: unified interface, modular architecture, type safety, and high performance. Its workflow involves a provider abstraction layer, smart agent invocation tools or query vector storage, and mechanisms such as retrieval-augmented generation (RAG) to generate responses.

Rig is suitable for building applications such as question-and-answer systems, document search tools, and context-aware chatbots.

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 functionalities of the Zerebro project but adopts a more modular and extensible design.

ZerePy provides a command line interface (CLI) for managing AI Agents, supporting OpenAI and Anthropic's LLMs, and directly integrates with the X platform API. Its modular connection system allows developers to add support for other social platforms or services.

Compared to Eliza, ZerePy focuses more on simplifying the deployment process of AI Agents on specific social platform (X), leaning towards practical applications.

2. The Replica of the BTC Ecosystem

The development path of AI Agents has similarities with the recent BTC ecosystem. The BTC ecosystem has gone through BRC20, multi-protocol competition, BTC L2, and now centers around BTCFi with Babylon. AI Agents are developing faster based on a mature AI technology stack, and the path can be summarized as: GOAT/ACT - Social type Agents/Analytical AI - Competition of Agent frameworks. In the future, infrastructure projects focusing on Agent Decentralization and security may become the main theme of the next stage.

AI Agent narrative is not about reproducing the history of smart contract chains; existing AI framework projects provide new infrastructure development ideas. Compared to Memecoin Launchpad and the Inscription Protocol, the AI framework resembles a future public chain, while Agents resemble future Dapps.

In the era of AI in the cryptocurrency industry, future debates may shift from EVM and heterogeneous chains to a framework contest. The key issue is how to achieve Decentralization or chaining, and the significance of developing these projects on the blockchain.

3. What is the significance of going on-chain?

When blockchain combines with other fields, it faces issues of significance. Considering the reasons for the success of DeFi ( high accessibility, high efficiency, low cost, and the security of decentralization without trust ), the reasons supporting Agent chainization may include:

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

2. Blockchain-based security solutions may become a necessity, especially when agents intervene in real or virtual wallets.

3. It may form unique blockchain financial gameplay, such as a model similar to LP in AMM, or new financial gameplay formed by Agents based on different application scenarios.

4. The agent combined with blockchain may achieve transparent and traceable reasoning, making it more attractive than the agent browsers provided by traditional internet giants.

4. Creative Economy

Framework projects may provide entrepreneurial opportunities similar to the GPT Store in the future. A framework that simplifies the Agent building process and offers complex functionality combinations may have an advantage, creating a more interesting Web3 creative economy than the GPT Store.

Compared to the GPT Store, the Web3 creative economy may be fairer, introducing a community economy that makes Agents more complete. This will be an opportunity for ordinary people to participate, and the future AI Memes may be smarter and more interesting than the Agents on existing platforms.