Author: Deep Value Memetics, Translation: Golden Finance Xiaozou
In this article, we will explore the prospects of Crypto X AI frameworks. We will focus on the current major four frameworks (ELIZA, GAME, ARC, ZEREPY) and their respective technical differences.
1. Introduction
In the past week, we have researched and tested the four major Crypto X AI frameworks: ELIZA, GAME, ARC, and ZEREPY, and our conclusions are as follows.
We believe that AI16Z will continue to dominate. The value of Eliza (approximately 60% market share, market value exceeding $1 billion) lies in its first-mover advantage (Lindy effect) and its increasing usage among developers, evidenced by data such as 193 contributors, 1,800 forks, and over 6,000 stars, making it one of the most popular codebases on GitHub.
So far, GAME (approximately 20% market share, market value around $300 million) has developed smoothly, gaining rapid adoption, as the VIRTUAL platform just announced, with over 200 projects, 150,000 daily requests, and a 200% weekly growth rate. GAME will continue to benefit from the rise of VIRTUAL and is expected to become one of the biggest winners in its ecosystem.
Rig (ARC, approximately 15% market share, market value around $160 million) is very noteworthy due to its modular design, which is very easy to operate, and it can dominate the Solana ecosystem (RUST) as a 'pure-play'.
Zerepy (approximately 5% market share, market value around $300 million) is a relatively niche application aimed specifically at the enthusiastic ZEREBRO community, and its recent collaboration with the ai16z community may generate synergistic effects.
We note that our market share calculations cover market value, development records, and the underlying operating system terminal market.
We believe that the framework's niche market will be the fastest-growing area in this market cycle, with a total market value of $1.7 billion potentially growing to $20 billion, which is still relatively conservative compared to the peak valuations of L1 in 2021 when many L1 valuations exceeded $20 billion. Although these frameworks serve different terminal markets (chains/ecosystems), given our belief that this field is on an upward trend, a market capitalization-weighted approach may be the most prudent method.
2. The Four Major Frameworks
In the table below, we list the key technologies, components, and advantages of each major framework.
(1) Framework Overview
In the intersecting field of AI X Crypto, several frameworks promote the development of AI. They are Eliza from AI16Z, Rig from ARC, Zerepy from ZEREBRO, and GAME from VIRTUAL. Each framework meets different needs and philosophies in the AI agent development process, ranging from open-source community projects to performance-oriented enterprise-level solutions.
This article will first introduce the frameworks, telling everyone what they are, what programming languages they use, their technical architecture, algorithms, what unique features they have, and what potential use cases the frameworks can employ. Then, we will compare each framework in terms of usability, scalability, adaptability, and performance, exploring their respective advantages and limitations.
ELIZA (developed by ai16z)
Eliza is a multi-agent simulation open-source framework designed for creating, deploying, and managing autonomous AI agents. It is developed in the TypeScript programming language, providing a flexible and scalable platform for building intelligent agents that can interact with humans across multiple platforms while maintaining consistent personality and knowledge.
The core functionalities of the framework include a multi-agent architecture that supports the simultaneous deployment and management of multiple unique AI personalities, as well as a role system that creates different agents using role file frameworks, and provides long-term memory and context-aware memory management capabilities through an advanced retrieval-augmented generation (RAG) system. Additionally, the Eliza framework offers smooth platform integration for reliable connections with Discord, X, and other social media platforms.
In terms of AI agent communication and media capabilities, Eliza is an excellent choice. In terms of communication, the framework supports integration with Discord's voice channel features, X functionalities, Telegram, and direct access to APIs for customized use cases. On the other hand, the framework's media processing capabilities extend to PDF document reading and analysis, link content extraction and summarization, audio transcription, video content processing, image analysis, and conversation summarization, effectively handling various media inputs and outputs.
The Eliza framework provides flexible AI model support through local inference of open-source models, OpenAI's cloud inference, and default configurations (such as Nous Hermes Llama 3.1B), and integrates support for Claude handling complex tasks. Eliza adopts a modular architecture with extensive operating system, custom client support, and a comprehensive API, ensuring scalability and adaptability between applications.
Eliza's use cases span multiple fields, including AI assistants for customer support, community auditing, and personal tasks, as well as social media roles such as content auto-creators, interactive bots, and brand representatives. It can also act as a knowledge worker, serving as research assistants, content analysts, and document processors, and supports interactive roles such as role-playing bots, educational mentors, and agent representatives.
Eliza's architecture is built around the agent runtime, which integrates seamlessly with its role system (supported by model providers), memory manager (connected to databases), and operating system (linked to platform clients). The framework's unique features include a plugin system that supports modular functionality extensions, multimodal interactions such as voice, text, and media, and compatibility with leading AI models (such as Llama, GPT-4, and Claude). With its diverse functionality and robust design, Eliza stands out as a powerful tool for developing AI applications across domains.
G.A.M.E (developed by Virtuals Protocol)
The Generative Autonomous Multimodal Entity Framework (G.A.M.E) aims to provide developers with API and SDK access for AI agent experimentation. This framework provides a structured approach to managing the behavior, decision-making, and learning processes of AI agents.
Its core components are as follows: first, the Agent Prompting Interface is the entry point for developers to access agent behavior by integrating GAME into agents. The Perception Subsystem initiates sessions by specifying parameters such as session ID, agent ID, user, and other relevant details.
It synthesizes incoming information into a format suitable for the Strategic Planning Engine, acting as an AI agent's sensory input mechanism, whether in the form of dialogue or reaction. At its core is the dialogue processing module, which handles messages and responses from the agent and collaborates with the perception subsystem to effectively interpret and respond to input.
The Strategic Planning Engine works together with the dialogue processing module and on-chain wallet operators to generate responses and plans. The engine's functionality has two levels: as a high-level planner, it creates broad strategies based on context or goals; as a low-level strategy, it translates these strategies into actionable plans, which are further divided into action planners for specified tasks and plan executors for executing tasks.
Another independent but important component is the World Context, which refers to the environment, global information, and game state, providing necessary context for the agent's decision-making. Additionally, the Agent Repository is used to store long-term attributes such as goals, reflections, experiences, and personalities that collectively shape the agent's behavior and decision-making processes.
The framework uses short-term working memory and long-term memory processors. The short-term memory retains relevant information from past behaviors, results, and current plans. In contrast, the long-term memory processor extracts key information based on criteria such as importance, recency, and relevance. Long-term memory stores knowledge such as the agent's experiences, reflections, dynamic personality, world context, and working memory to enhance decision-making and provide a basis for learning.
The learning module generates general knowledge from data sourced from the perception subsystem, which is fed back into the system to improve future interactions. Developers can input feedback about actions, game states, and sensory data through the interface to enhance the learning capabilities of AI agents, improving their planning and decision-making capabilities.
The workflow begins with developers interacting through the agent prompting interface. Input is processed by the perception subsystem and forwarded to the dialogue processing module, which manages the interaction logic. The Strategic Planning Engine then formulates and executes plans based on this information, utilizing high-level strategies and detailed action plans.
Data from the world context and agent repository informs these processes, while working memory tracks immediate tasks. Meanwhile, the long-term memory processor stores and retrieves long-term knowledge. The learning module analyzes results and integrates new knowledge into the system, allowing the agent's behavior and interactions to be continuously improved.
RIG (developed by ARC)
Rig is an open-source Rust framework designed to simplify the development of large language model applications. It provides a unified interface for interacting with multiple LLM providers (such as OpenAI and Anthropic) and supports various vector storage, including MongoDB and Neo4j. The framework's modular architecture is unique in its core components, such as the Provider Abstraction Layer, vector store integration, and agent system, facilitating seamless interaction with LLMs.
Rig's primary audience includes developers building AI/ML applications in Rust, followed by organizations seeking to integrate multiple LLM providers and vector storage into their own Rust applications. The repository uses a workspace architecture with multiple crates, supporting scalability and efficient project management. Key features include a provider abstraction layer that standardizes the completion and embedding of APIs across different LLM providers, with consistent error handling. The Vector Store Integration component provides an abstract interface for multiple backends and supports vector similarity searches. The agent system simplifies LLM interactions, supporting retrieval-augmented generation (RAG) and tool integration. Additionally, the embedding framework provides batch processing capabilities and type-safe embedding operations.
Rig leverages multiple technical advantages to ensure reliability and performance. Asynchronous operations utilize Rust's asynchronous runtime to effectively handle a large number of concurrent requests. The inherent error handling mechanisms of the framework improve recovery from AI provider or database operation failures. Type safety can prevent errors during the compilation process, enhancing code maintainability. Efficient serialization and deserialization processes support data processing in formats like JSON, which is crucial for AI service communication and storage. Detailed logging and detection further assist in debugging and monitoring applications.
The workflow of Rig starts when a request is initiated by the client, which interacts with the appropriate LLM model through the provider abstraction layer. The data is then processed by the core layer, where the agent can use tools or access contextual vector storage. The response is generated and refined through a complex workflow (such as RAG) before being returned to the client, involving document retrieval and context understanding. The system integrates multiple LLM providers and vector storage, adapting to model availability or performance updates.
Rig's use cases are diverse, including question-answer systems for retrieving relevant documents to provide accurate responses, document search and retrieval systems for efficient content discovery, and chatbots or virtual assistants providing context-aware interaction for customer service or education. It also supports content generation, enabling the creation of texts and other materials based on learning patterns, making it a versatile tool for developers and organizations.
Zerepy (developed by ZEREPY and blorm)
ZerePy is an open-source framework written in Python, designed to deploy agents on X leveraging OpenAI or Anthropic LLM. It is a modular version derived from the Zerebro backend, allowing developers to launch agents with core functionalities similar to Zerebro. While the framework provides a foundation for agent deployment, fine-tuning the model is essential for generating creative outputs. ZerePy simplifies the development and deployment of personalized AI agents, particularly for content creation on social platforms, fostering an AI-driven creative ecosystem focused on art and decentralized applications.
The framework is developed using Python, emphasizing agent autonomy and focusing on creative output generation, aligning with Eliza's architecture and collaboration. Its modular design supports memory system integration, allowing agents to be deployed on social platforms. Key features include a command-line interface for agent management, integration with Twitter, support for OpenAI and Anthropic LLMs, and a modular connection system for enhanced functionality.
ZerePy's use cases cover the social media automation domain, allowing users to deploy AI agents for posting, replying, liking, and sharing, thereby increasing platform engagement. Additionally, it caters to content creation in areas such as music, memes, and NFTs, making it an important tool for digital art and blockchain-based content platforms.
(2) Comparison of the Four Major Frameworks
In our view, each framework offers a unique approach to AI development that aligns with specific needs and environments, shifting our focus from the competitive relationship among these frameworks to the uniqueness of each framework.
ELIZA stands out with its user-friendly interface, especially for developers familiar with JavaScript and Node.js environments. Its comprehensive documentation aids in setting up AI agents across various platforms, although its extensive feature set may pose a certain learning curve. Developed in TypeScript, Eliza is an ideal choice for building agents embedded in the web, as most web infrastructure frontends are developed using TypeScript. The framework is known for its multi-agent architecture, allowing deployment of different AI personalities on platforms like Discord, X, and Telegram. Its advanced memory management RAG system makes it particularly effective for AI assistants in customer support or social media applications. While it offers flexibility, strong community support, and consistent cross-platform performance, it is still in its early stages and may pose a learning curve for developers.
GAME is designed specifically for game developers, providing a low-code or no-code interface through APIs, making it accessible to less technically inclined users in the gaming field. However, its focus on game development and blockchain integration may present a steep learning curve for those without relevant experience. It stands out in program content generation and NPC behavior but is limited by the added complexity of its niche and blockchain integration.
Due to the use of the Rust language, Rig may not be very user-friendly, given the complexity of the language, which presents significant learning challenges, but it offers intuitive interactions for those proficient in system programming. Compared to TypeScript, this programming language is renowned for its performance and memory safety. It features strict compile-time checks and zero-cost abstractions, essential for running complex AI algorithms. The language is highly efficient, and its low-level control makes it an ideal choice for resource-intensive AI applications. The framework provides high-performance solutions with modular and scalable designs, making it suitable for enterprise applications. However, developers unfamiliar with Rust will inevitably face a steep learning curve when using it.
ZerePy leverages Python, providing high availability for creative AI tasks, with a lower learning curve for Python developers, especially those with an AI/ML background, and benefiting from strong community support due to Zerebro's crypto community. ZerePy excels in creative AI applications such as NFTs, positioning itself as a powerful tool for digital media and art. While it thrives in creativity, its scope is relatively narrow compared to other frameworks.
In terms of scalability, ELIZA has made significant progress in its V2 update, introducing a unified message line and an extensible core framework supporting effective management across multiple platforms. However, without optimization, managing this multi-platform interaction may pose scalability challenges.
GAME excels in real-time processing required for games, with scalability managed through efficient algorithms and potential blockchain distributed systems, although it may be limited by specific game engines or blockchain networks.
The Rig framework utilizes Rust's scalability performance, designed for high-throughput applications, particularly effective for enterprise-level deployments, although achieving true scalability may require complex setups.
Zerepy's scalability focuses on creative output, supported by community contributions, but its concentrated focus may limit its application in a broader AI context; scalability may be tested by the diversity of creative tasks rather than by user numbers.
In terms of adaptability, ELIZA leads with its plugin system and cross-platform compatibility, while GAME and Rig excel in gaming environments and handling complex AI tasks. ZerePy shows high adaptability in creative fields but is less suitable for broader AI applications.
In terms of performance, ELIZA is optimized for fast social media interactions, where quick response times are key, but its performance may vary when handling more complex computational tasks.
GAME developed by Virtual Protocol focuses on high-performance real-time interactions in gaming scenarios, utilizing efficient decision-making processes and potential blockchain for decentralized AI operations.
The Rig framework is based on the Rust language, providing excellent performance for high-performance computing tasks, suitable for enterprise applications where computational efficiency is critical.
Zerepy's performance is tailored for the creation of creative content, with metrics centered on the efficiency and quality of content generation, which may not be as universally applicable outside the creative domain.
The advantage of ELIZA lies in its flexibility and scalability, providing high adaptability through its plugin system and role configurations, facilitating cross-platform social AI interactions.
GAME provides unique real-time interaction features in gaming, enhanced by blockchain integration for novel AI engagement.
The advantage of Rig lies in its performance and scalability for enterprise AI tasks, focusing on providing clean modular code for the health of long-term projects.
Zerepy excels in nurturing creativity, leading in applications of AI in digital art, supported by a vibrant community-driven development model.
Each framework has its limitations; ELIZA is still in its early stages and may face potential stability issues and a learning curve for new developers, the niche nature of Game may limit broader applications, and blockchain adds complexity, while Rig's steep learning curve due to Rust may deter some developers. Zerepy's narrow focus on creative output may limit its use in other AI domains.
(3) Framework Comparison Summary
Rig (ARC):
Language: Rust, focusing on safety and performance.
Use case: Ideal for enterprise-level AI applications due to its focus on efficiency and scalability.
Community: Less community-driven, focusing more on technical developers.
Eliza (AI16Z):
Language: TypeScript, emphasizing the flexibility of web3 and community involvement.
Use cases: Designed for social interactions, DAOs, and trading, with a particular emphasis on multi-agent systems.
Community: Highly community-driven with extensive GitHub participation.
ZerePy (ZEREBRO):
Language: Python, making it accessible to a broader base of AI developers.
Use cases: Suitable for social media automation and simpler AI agent tasks.
Community: Relatively new, but expected to grow due to the popularity of Python and support from AI16Z contributors.
GAME (VIRTUAL):
Focus: Autonomous, adaptive AI agents that can evolve based on interactions in a virtual environment.
Use case: Most suitable for AI agent learning and adaptation scenarios, such as games or virtual worlds.
Community: An innovative community, but still determining its positioning in the competition.
3. Github Star Data Trends
The above figure shows GitHub star tracking data since the release of these frameworks. It is worth noting that GitHub stars are indicators of community interest, project popularity, and perceived value of the project.
ELIZA (red line):
Starting from a low base in July, the star count has surged to 61,000 by late November, indicating a rapid increase in interest that has attracted the attention of developers. This exponential growth suggests that ELIZA has gained immense traction due to its functionality, updates, and community involvement. Its popularity far exceeds that of other competitors, indicating strong community support and broader applicability or interest in the AI community.
RIG (blue line):
Rig is the longest-established among the four major frameworks, with a moderate but consistently growing number of stars, likely to increase significantly over the next month. It has reached 1,700 stars but is still on the rise. Ongoing development, updates, and an increasing user base account for the continuous accumulation of user interest. This may reflect a niche user base or a reputation still in the making.
ZEREPY (yellow line):
ZerePy was just launched a few days ago and has already accumulated 181 stars. It is worth emphasizing that ZerePy needs more development to enhance its visibility and adoption. Collaboration with AI16Z may attract more code contributors.
GAME (green line):
This project had the fewest stars, and it is noteworthy that this framework can be applied directly to agents in the virtual ecosystem via API, eliminating the need for GitHub visibility. However, this framework was only made publicly available to builders just over a month ago, and over 200 projects are using GAME to build.
4. Reasons for Framework Optimism
The V2 version of Eliza will integrate the Coinbase agent suite. All projects using Eliza will support native TEE in the future, allowing agents to operate in a secure environment. One upcoming feature of Eliza is the Plugin Registry, enabling developers to seamlessly register and integrate plugins.
In addition, Eliza V2 will support automated anonymous cross-platform messaging. The token economics white paper is scheduled for release on January 1, 2025, which is expected to have a positive impact on the underlying AI16Z token of the Eliza framework. AI16Z plans to continue enhancing the framework's utility and attract high-quality talent, with the efforts of its main contributors already demonstrating its capability.
The GAME framework provides no-code integration for agents, allowing GAME and ELIZA to be used simultaneously within a single project, each serving specific purposes. This approach is expected to attract builders who focus on business logic rather than technical complexity. Although the framework has only been publicly released for about 30 days, it has made substantial progress with the team's efforts to attract more contributors. All projects launched on VIRTUAL are expected to use GAME.
Rig, represented by the ARC token, has enormous potential, although its framework is still in the early growth phase, and the plans to drive project adoption have only been launched for a few days. However, high-quality projects adopting ARC are expected to emerge soon, similar to the Virtual flywheel but focused on Solana. The team is optimistic about its partnership with Solana, comparing the relationship between ARC and Solana to that of Virtual and Base. Notably, the team encourages not only new projects to launch using Rig but also developers to enhance the Rig framework itself.
Zerepy is a newly launched framework that is gaining attention due to its collaboration with Eliza. The framework attracts Eliza's contributors, who are actively improving it. Driven by ZEREBRO fans, it has a passionate following and offers new opportunities for Python developers who previously lacked representation in the AI infrastructure competition. This framework will play an important role in AI creativity.