Deconstructing AI Frameworks: From Intelligent Agents to Decentralization Exploration

Introduction

Recently, the narrative of the combination of AI and cryptocurrency has developed rapidly. Market attention is focused on technology-driven "framework-type" projects, with multiple projects emerging in this niche that have market capitalizations exceeding one billion or even ten billion in a short period of time. These projects have given rise to new asset issuance models, namely issuing tokens based on code repositories, and Agents developed from frameworks can also issue tokens again. Based on the framework, Agents serve as upper-layer applications, forming a unique infrastructure model for the AI era. This article will explore the significance of AI frameworks for the cryptocurrency industry starting from the concept of frameworks.

1. What is a framework?

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

Although the "AI framework" is a new concept in the cryptocurrency field, it has been nearly 14 years since Theano was introduced in 2010. There are mature frameworks available in the traditional AI field, such as TensorFlow and Pytorch. The framework projects emerging in cryptocurrency are developed in response to the demand for Agents under the AI boom and extend to other fields. Here are several mainstream frameworks introduced below:

1.1 Eliza

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

1.2 G.A.M.E

G.A.M.E is an automated multi-modal AI framework designed mainly for intelligent NPCs in games. Its feature is that it can be used by low-code or even no-code users.

The core architecture includes multiple modules such as the Agent prompt interface, perception subsystem, and strategic planning engine, which work collaboratively to achieve functionality.

The application scenarios mainly focus on the decision-making, feedback, perception, and personality of Agents in virtual environments, suitable for games and the metaverse.

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 to interact with multiple LLM service providers and vector databases.

Core features:

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

The workflow includes steps such as request processing, information retrieval, and response generation.

Suitable for building Q&A systems, document search tools, chatbots, and other applications.

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.

The core architecture includes:

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

Compared to Eliza, ZerePy focuses more on simplifying the deployment of AI Agents on specific social platforms.

2. The Replica of the BTC Ecosystem

The development path of AI Agents is similar to the recent BTC ecosystem: BTC ecosystem: BRC20 → multi-protocol competition → BTC L2 → BTCFi AI Agent: GOAT/ACT → Multi-type Agent/Framework Competition → Decentralization Infrastructure

However, the AI Agent track is unlikely to lead to homogenization or bubble. The AI framework is more like the public chain of the future, while the Agent is more like the Dapp of the future. Future debates may shift from the conflict between EVM and heterogeneous chains to a framework competition, with the key issue being how to achieve Decentralization and its significance on the blockchain.

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

The core issue facing the combination of blockchain and AI is its significance. Referring to the successful experience of DeFi, the reasons supporting the chainification of agents may include:

1. Reduce usage costs, improve accessibility and choice.
2. Provide blockchain-based security solutions
3. Form unique blockchain financial gameplay
4. Achieve transparent and traceable reasoning to improve interoperability.

4. Creative Economy

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

Compared to the GPT Store, the Web3 Agent creative economy may be more open and fair, introducing a community economy that makes the Agent more complete. This will be an opportunity for ordinary people to participate, and future AI Memes may also be smarter and more interesting.