This article comes from: Deep Value Memetics
Compilation | Odaily Planet Daily (@OdailyChina)
Translator | Azuma (@azuma_eth)
Key Points Overview
In this report, we discuss the development landscape of several mainstream frameworks in the Crypto AI space. We will examine the four major frameworks currently — Eliza (AI16Z), G.A.M.E (GAME), Rig (ARC), and ZerePy (ZEREBRO), analyzing their technical differences and growth potential.
In the past week, we have analyzed and tested the four major frameworks, and the conclusions are summarized as follows.
We believe that Eliza (with a market share of approximately 60%, valued at around 900 million USD when the original author wrote this, and approximately 1.4 billion USD as of the publication date) will continue to dominate market share. Eliza's value lies in its first-mover advantage and accelerated adoption by developers, as evidenced by 193 contributors on GitHub, 1800 forks, and over 6000 stars, making it one of the most popular software libraries on GitHub.
G.A.M.E (with a market share of approximately 20%, valued at around 300 million USD when the original author wrote this, and approximately 257 million USD as of the publication date) has been developing very smoothly so far and is experiencing rapid adoption, as noted in an earlier announcement from Virtuals Protocol, where over 200 projects have been built based on G.A.M.E, with daily request counts exceeding 150,000, and a weekly growth rate of over 200%. G.A.M.E will continue to benefit from the explosion of VIRTUAL and could potentially become one of the biggest winners in that ecosystem.
Rig (with a market share of approximately 15%, valued at around 160 million USD when the original author wrote this, and approximately 279 million USD as of the publication date) features a modular design that is very appealing and easy to operate, and is expected to dominate the Solana ecosystem (RUST).
Zerepy (with a market share of approximately 5%, valued at around 300 million USD when the original author wrote this, and approximately 424 million USD as of the publication date) is a more niche application, specific to a fervent ZEREBRO community, and its recent collaboration with the ai16z community may produce some synergistic effects.
In the above statistics, 'market share' considers market capitalization, development records, and the breadth of the underlying operating system end markets.
We believe that AI frameworks will become the fastest-growing segment in this cycle, with the current total market cap of approximately 1.7 billion USD easily growing to 20 billion USD, and this figure may still be conservative compared to the peak valuation of Layer 1 in 2021 — when many single projects were valued at over 20 billion USD. While the frameworks mentioned above serve different end markets (chains/ecosystems), given our belief that this sector will grow overall, a market-cap-weighted approach may be relatively prudent.
Four Major Frameworks
At the intersection of AI and Crypto, several frameworks aimed at accelerating AI development have emerged, including Eliza (AI16Z), G.A.M.E (GAME), Rig (ARC), and ZerePy (ZEREBRO). From open-source community projects to performance-focused enterprise solutions, each framework caters to different needs and philosophies in agent development.
In the table below, we list the key technologies, components, and advantages of each framework.
This report will first focus on what these frameworks are, the programming languages they use, their technical architectures, algorithms, and unique features with potential use cases. Then we will compare each framework based on usability, scalability, adaptability, and performance, while discussing their advantages and limitations.
Eliza
Eliza is an open-source multi-agent simulation framework developed by ai16z, aimed at creating, deploying, and managing autonomous AI agents. It is developed using TypeScript as the programming language, providing a flexible and scalable platform for building intelligent agents that can interact with humans across multiple platforms while maintaining a consistent personality and knowledge.
The core functionalities of the framework include: support for deploying and managing multiple unique AI personalities within a multi-agent architecture; a role system for creating diverse agents using role file frameworks; providing long-term memory and context-aware memory management capabilities through an advanced retrieval-augmented generation system (RAG). Additionally, the Eliza framework offers smooth platform integration, enabling reliable connections with Discord, X, and other social media platforms.
In terms of communication and media capabilities for AI agents, Eliza is an excellent choice. In communication, this framework supports integration with Discord's voice channel features, X functionality, Telegram, and direct API access for custom use cases. On the other hand, the framework's media processing capabilities have expanded to include PDF document reading and analysis, content extraction and summarization, audio transcription, video content processing, image analysis, and conversation summarization, effectively handling a variety of media input and output.
Eliza provides flexible AI model support, enabling local inference using open-source models, cloud-based inference using default configurations such as OpenAI and Nous Hermes Llama 3.1 B, and supports integration with Claude for handling complex queries. Eliza adopts a modular architecture, featuring an extensive action system, custom client support, and comprehensive APIs, ensuring scalability and adaptability across applications.
Eliza's use cases span multiple areas, such as AI assistants related to customer support, community management, and personal tasks; automated content creators, brand representatives, and other social media roles; it can also act as a knowledge worker, playing roles such as research assistants, content analysts, and document processors; as well as interactive roles such as role-playing robots, educational tutors, and agent proxies.
The architecture of Eliza is built around an agent runtime that seamlessly integrates with a role system (supported by model providers), a memory manager (connected to a database), and an action system (linked to platform clients). The framework's unique features include a plugin system that allows for modular functionality extensions, supporting multimodal interactions such as voice, text, and media, as well as compatibility with leading AI models like Llama, GPT-4, and Claude. With its multifunctionality and robust design, Eliza becomes a powerful tool for cross-domain AI application development.
G.A.M.E
G.A.M.E is developed by the official Virtuals team, standing for 'Generative Autonomous Multimodal Entities Framework', which aims to provide developers with application programming interfaces (APIs) and software development kits (SDKs) to experiment with AI agents. The framework provides a structured approach to managing the behavior, decision-making, and learning processes of AI agents.
The core components of G.A.M.E are as follows: First, the 'Agent Prompting Interface' is the entry point for developers to integrate G.A.M.E into agents for obtaining agent behaviors.
The 'Perception Subsystem' initiates sessions by specifying parameters such as session ID, agent ID, user, and other relevant details. It synthesizes incoming messages into a format suitable for the 'Strategic Planning Engine', serving as the sensory input mechanism for AI agents, whether in the form of dialogue or reactions. Central to this is the 'Dialogue Processing Module', responsible for handling messages and responses from agents and collaborating with the 'Perception Subsystem' to effectively interpret and respond to inputs.
The 'Strategic Planning Engine' works in conjunction with the 'Dialogue Processing Module' and the 'On-Chain Wallet Operator' to generate responses and plans. This engine operates on two levels: as a high-level planner that creates broad strategies based on context or objectives; and as a low-level strategist that translates these strategies into executable policies, further broken down into action planners (for specifying tasks) and plan executors (for executing tasks).
A separate but key component is the 'World Context', which references environmental, world information, and game state to provide necessary context for the agent's decision-making. Additionally, the 'Agent Library' is used to store long-term attributes such as goals, reflections, experiences, and personalities, which collectively shape the agent's behavior and decision-making process. The framework utilizes 'Short-Term Working Memory' and 'Long-Term Memory Processor' — short-term memory retains relevant information about previous actions, outcomes, and current plans; in contrast, the long-term memory processor extracts key information based on criteria such as importance, recency, and relevance. This memory stores knowledge about the agent's experiences, reflections, dynamic personalities, world context, and working memory to enhance decision-making and provide a foundation for learning.
To enhance the layout, the 'Learning Module' retrieves data from the 'Perception Subsystem' to generate general knowledge, which is fed back into the system to optimize future interactions. Developers can input feedback on actions, game states, and sensory data through the interface, enhancing AI agents' learning and improving their planning and decision-making capabilities.
The workflow begins with developers interacting through the agent prompting interface; the 'Perception Subsystem' processes inputs and forwards them to the 'Dialogue Processing Module', which manages interaction logic; then, the 'Strategic Planning Engine' formulates and executes plans using high-level strategies and detailed action planning based on this information.
Data from 'World Context' and 'Agent Library' informs these processes, while working memory tracks immediate tasks. Meanwhile, the 'Long-Term Memory Processor' stores and retrieves knowledge over time. The 'Learning Module' analyzes results and integrates new knowledge into the system, allowing agents' behaviors and interactions to improve continuously.
Rig
Rig is an open-source framework based on Rust, aimed at simplifying the development of large language model (LLM) 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 features core components such as the 'Provider Abstraction Layer', 'Vector Storage Integration', and 'Agent System', facilitating seamless interactions with LLMs.
The primary audience for Rig includes developers building AI/ML applications using Rust, with a secondary audience being organizations looking to integrate multiple LLM providers and vector storage into their Rust applications. The resource library is organized using a workspace-based structure, containing multiple crates, achieving scalability and efficient project management. Rig's main features include the Provider Abstraction Layer, which standardizes API interactions with LLM providers through consistent error handling; the vector storage 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 efficiently handle a large volume of concurrent requests; the framework's inherent error handling mechanisms enhance recovery capabilities from failures in AI provider or database operations; type safety prevents compile-time errors, thereby improving code maintainability; efficient serialization and deserialization processes help handle data in formats like JSON, which is critical for communication and storage in AI services; detailed logging and instrumentation further assist in debugging and monitoring applications.
The workflow in Rig begins with the client initiating a request, which flows through the 'Provider Abstraction Layer' to interact with the corresponding LLM models; then, data is processed by the core layer, where agents can use tools or access vector storage for context; responses are generated and refined through complex workflows like RAG, which includes document retrieval and contextual understanding, before being returned to the client. The system integrates multiple LLM providers and vector storage, adapting to changes in model availability or performance.
Rig's use cases are diverse, including question-answer systems for retrieving relevant documents to provide accurate responses, document search and retrieval for efficient content discovery, and chatbots or virtual assistants providing context-aware interactions for customer service or education. It also supports content generation, capable of creating text and other materials based on learned patterns, making it a versatile tool for developers and organizations.
ZerePy
ZerePy is an open-source framework written in Python, designed to deploy agents on X utilizing OpenAI or Anthropic LLMs. ZerePy is derived from a modular version of the Zerebro backend, allowing developers to launch agents using functionalities similar to Zerebro's core features. While the framework provides a foundation for deploying agents, fine-tuning of the model is necessary to produce creative outputs. ZerePy simplifies the development and deployment of personalized AI agents, especially suitable for content creation on social platforms, fostering an AI creative ecosystem focused on art and decentralized applications.
This framework is built using Python, emphasizing the autonomy of agents, focusing on the generation of creative outputs, in alignment with the architecture of Eliza + partnership. Its modular design supports memory system integration, making it easier to deploy agents on social platforms. Its main features include a command-line interface for agent management, integration with X, support for OpenAI and Anthropic LLMs, and a modular connection system for enhanced functionality.
ZerePy's use cases cover social media automation, allowing users to deploy AI agents for posting, replying, liking, and sharing, thus enhancing platform engagement. Additionally, it is suitable for content creation in areas such as music, memos, and NFTs, making it an important tool for digital art and blockchain-based content platforms.
Horizontal Comparison
In our opinion, each of the frameworks mentioned above offers a unique approach to AI development, catering to specific needs and environments, shifting the debate from whether these frameworks are competitors to whether each framework provides unique utility and value.
Eliza stands out with its user-friendly interface, particularly suitable for developers familiar with JavaScript and Node.js environments. Its comprehensive documentation aids in setting up AI agents across various platforms, although its rich feature set may present a moderate learning curve; due to the use of TypeScript, Eliza is very suitable for building agents embedded in web environments, as most front-end web infrastructure is built with TypeScript. The framework is known for its multi-agent architecture, capable of deploying diverse AI personality agents across platforms such as Discord, X, and Telegram. Its advanced RAG system is used for memory management, making it particularly suitable for building AI assistants for customer support or social media application types. While it offers flexibility, strong community support, and consistent cross-platform performance, it is still in its early stages, which may pose a learning curve for developers.
G.A.M.E is designed for game developers, providing a low-code or no-code interface through API, making it accessible to users with lower technical skills in the gaming field. However, it focuses on game development and blockchain integration, which may present a steep learning curve for those without relevant experience. It excels in procedural content generation and NPC behavior, but is also limited by its niche domain and the additional complexities that come with blockchain integration.
Rig may be less user-friendly due to the complexity of the Rust language, presenting significant challenges for learning, but it can offer intuitive interactions for those proficient in systems programming. Compared to TypeScript, Rust is known for its performance and memory safety. It features strict compile-time checks and zero-cost abstractions, essential for running complex AI algorithms. The efficient and low-control characteristics of the language make it an ideal choice for resource-intensive AI applications. The framework adopts a modular and scalable design, providing high-performance solutions, making it very suitable for enterprise applications. However, for developers unfamiliar with the Rust language, using Rust presents a steep learning curve.
ZerePy uses Python, providing higher usability for creative AI tasks. For Python developers, especially those with an AI/ML background, the learning curve is lower, and due to ZEREBRO's popularity, strong community support is available. ZerePy excels in creative AI applications such as NFTs, positioning itself as a powerful tool in the digital media and arts field. While it performs excellently in creativity, its application scope is relatively narrow compared to other frameworks.
In terms of scalability, the comparisons of the four major frameworks are as follows.
Eliza has made significant progress after the V2 version update, introducing a unified message line and an extensible core framework, achieving efficient management across platforms. However, without optimization, managing this multi-platform interaction may pose scalability challenges.
G.A.M.E excels in the real-time processing required for games, and its scalability can be managed through efficient algorithms and potential blockchain distributed systems, although it may be constrained by specific game engine or blockchain network limitations.
The Rig framework can utilize the performance advantages of Rust to achieve better scalability, inherently designed for high-throughput applications, which may be particularly effective for enterprise-level deployments, though achieving true scalability may require complex setups.
ZerePy's scalability is tailored to creative output and supported by community contributions, but the framework's focus may limit its application in a broader AI environment, with its scalability potentially tested by the diversity of creative tasks rather than user volume.
In terms of applicability, Eliza, with its plugin system and cross-platform compatibility, is far ahead, followed by G.A.M.E in gaming environments and Rig for handling complex AI tasks. ZerePy has shown high adaptability in the creative domain but is less applicable in broader AI applications.
In terms of performance, the test results of the four major frameworks are as follows.
Eliza is optimized for rapid interactions on social media, but its performance may vary when handling more complex computational tasks.
G.A.M.E focuses on high-performance real-time interactions in gaming scenarios, leveraging efficient decision-making processes and potential blockchain for decentralized AI operations.
Rig, based on Rust, offers excellent performance for high-performance computing tasks, suitable for enterprise applications where computational efficiency is crucial.
ZerePy's performance is geared towards the creation of creative content, with metrics centered around the efficiency and quality of content generation, which may not be as universal beyond the creative domain.
Combining the aforementioned advantages and disadvantages, Eliza offers better flexibility and scalability, with its plugin system and role configuration providing strong adaptability, beneficial for cross-platform social AI interaction; G.A.M.E offers unique real-time interaction capabilities in gaming scenarios and provides novel AI participation through blockchain integration; Rig's advantages lie in its performance and scalability, suitable for enterprise-level AI tasks, emphasizing code simplicity and modularity to ensure the long-term healthy development of projects; Zerepy excels in fostering creativity, leading in AI applications for digital art, supported by a vibrant community-driven development model.
In summary, each framework has its limitations. Eliza is still in its early stages, with potential stability issues and a steep learning curve for new developers; G.A.M.E's niche focus may limit its broader application, and introducing blockchain adds complexity; Rig's learning curve is steeper due to the complexity of the Rust language, which may deter some developers; Zerepy's narrow focus on creative output may limit its application in other areas of AI.
Core Comparison Items
Rig (ARC)
Language: Rust, focusing on safety and performance.
Use Cases: Emphasizing efficiency and scalability, ideal for enterprise-level AI applications.
Community: Less community-driven, focusing more on technical developers.
Eliza (AI16Z)
Language: TypeScript, emphasizing the flexibility and community involvement of Web3.
Use Cases: Designed for social interaction, DAOs, and transactions, with a particular emphasis on multi-agent systems.
Community: Highly community-driven, with extensive ties to GitHub.
ZerePy (ZEREBRO):
Language: Python, more easily accepted by a broader AI developer community.
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.
G.A.M.E (VIRTUAL, GMAE):
Key Focus: Autonomous, adaptive AI agents that can evolve based on interactions in virtual environments.
Use Cases: Most suitable for scenarios where agents need to learn and adapt, such as games or virtual worlds.
Community: Innovative but still determining its position in competition.
Github Data Growth Trends
The chart above shows the changes in star data on GitHub since these frameworks were launched. Generally, GitHub stars can serve as indicators of community interest, project popularity, and perceived value of the project.
Eliza (Red Line): The chart shows a significant increase in star count for this framework, with a stable trend, starting from a low base in July, surging significantly in late November, now reaching 6100 stars. This indicates a rapid surge in interest around this framework, attracting developer attention. The exponential growth suggests that Eliza has gained immense appeal due to its functionality, updates, and community engagement, far surpassing other products, indicating strong community support and broader applicability or interest in the AI community.
Rig (Blue Line): Rig is the most historically established of the four major frameworks, with a modest yet stable growth in stars, showing a noticeable increase in the past month. Its total star count has reached 1700 but is still on an upward trajectory. The stable accumulation of attention is due to ongoing development, updates, and a growing user base. This may reflect that Rig is still in the process of building its reputation.
ZerePy (Yellow Line): ZerePy just launched a few days ago, and the star count has grown to 181. It is important to emphasize that ZerePy needs more development to improve its visibility and adoption rate, and collaboration with ai16z may attract more contributors to its codebase.
G.A.M.E (Green Line): This framework has a small number of stars, but it is noteworthy that it can be directly applied to agents in the Virtual ecosystem via API, eliminating the need for public release on GitHub. However, even though this framework has only been publicly available for builders for a little over a month, there are already over 200 projects utilizing G.A.M.E for building.
Expectations for Upgrades to AI Frameworks
Eliza's version 2.0 will include integration with the Coinbase agent toolkit. All projects utilizing Eliza will gain support for future native TEE (Trusted Execution Environment), allowing agents to operate in secure environments. The Plugin Registry is a forthcoming feature of Eliza that will allow developers to seamlessly register and integrate plugins.
Additionally, Eliza 2.0 will support automated anonymous cross-platform messaging. The Tokenomics white paper expected to be released on January 1, 2025 (relevant proposals have been announced) will have a positive impact on the AI16Z token supporting the Eliza framework. ai16z plans to continue enhancing the framework's practicality and leverage the efforts of its main contributors to bring in high-quality talent.
The G.A.M.E framework offers no-code integration for agents, allowing G.A.M.E and Eliza to be used simultaneously within a single project, each serving specific use cases. This approach is expected to attract builders focused on business logic rather than technical complexity. Although this framework has only been publicly available for over 30 days, it has made substantial progress with the team's efforts to attract more contributor support. Every project launched on VirtualI is expected to adopt G.A.M.E.
The Rig framework, powered by the ARC token, has significant potential, though its framework's growth is still in early stages, with the project contracts driving Rig adoption only going live a few days ago. However, high-quality projects are expected to emerge soon that pair with ARC, similar to the Virtual flywheel but focused on Solana. The Rig team is optimistic about collaborating with Solana, positioning ARC as the Virtual of Solana. Notably, the team not only incentivizes new projects launched with Rig but also encourages developers to enhance the Rig framework itself.
Zerepy is a newly launched framework, gaining significant attention due to collaboration with ai16z (the Eliza framework). This framework has attracted contributors from Eliza who are actively working to improve it. Zerepy enjoys enthusiastic support driven by the ZEREBRO community and is opening new opportunities for Python developers who previously had limited space to play in the competitive AI infrastructure field. It is expected that this framework will play an important role in the creative aspects of AI.