Article reprint source: Odaily Planet Daily
This article comes from: Deep Value Memetics
Compiled by Odaily Planet Daily (@OdailyChina)
Translator｜Azuma (@azuma_eth)
Summary of key points
In this report, we discuss the development of several major frameworks in the field of Crypto & AI. We will examine the current four major frameworks - Eliza (AI16Z), G.A.M.E (GAME), Rig (ARC), ZerePy (ZEREBRO), and analyze their technical differences and development potential.
In the past week, we have analyzed and tested the above four frameworks, and the conclusions are summarized as follows.
We believe Eliza (~60% market share, ~$900M market cap at time of writing, ~$1.4B market cap as of writing) will continue to dominate market share. Eliza’s value lies in its first-mover advantage and accelerated developer adoption, as evidenced by 193 contributors, 1,800 forks, and over 6,000 stars on Github, making it one of the most popular repositories on Github.
G.A.M.E (~20% market share, ~$300 million at the time of writing, ~$257 million at the time of writing) has been very successful so far and is experiencing rapid adoption, as Virtuals Protocol announced earlier, with over 200 projects built on G.A.M.E, over 150,000 requests per day, and over 200% weekly growth. G.A.M.E will continue to benefit from the explosion of VIRTUAL and has the potential to be one of the biggest winners in the ecosystem.
Rig (market share ~15%, market cap ~$160M at time of writing, market cap ~$279M at time of writing) is very attractive and easy to operate with its modular design, and is expected to be a dominant player in the Solana ecosystem (RUST).
Zerepy (market share ~5%, market cap ~$300M at time of writing, market cap ~$424M as of writing) is a more niche application, specific to an avid ZEREBRO community, and its recent collaboration with the ai16z community may yield some synergies.
In the above statistics, "market share" is calculated by taking into account market capitalization, development record, and the breadth of the underlying operating system terminal market.
We believe AI frameworks will be the fastest growing sector in this cycle, and the current total market cap of the sector of about $1.7 billion will easily grow to $20 billion, which may still be conservative compared to the peak Layer1 valuation in 2021 - when many single projects were valued at more than $20 billion. Although the above frameworks serve different end markets (chains/ecosystems), given that we believe this sector will grow as a whole, a market cap-weighted approach may be relatively prudent.
Four major frameworks
At the intersection of AI and Crypto, several frameworks have emerged to accelerate AI development, 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 of 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, technical architectures, algorithms, and unique features with potential use cases. We will then compare each framework based on ease of use, scalability, adaptability, and performance, while discussing their strengths and limitations.
Eliza
Eliza is an open source multi-agent simulation framework developed by ai16z, designed to create, deploy and manage autonomous AI agents. It is developed in TypeScript as a programming language and provides a flexible and extensible platform for building intelligent agents that are able to interact with humans on multiple platforms while maintaining consistent personality and knowledge.
The core features of the framework include: a multi-agent architecture that supports the simultaneous deployment and management of multiple unique AI personalities; a role system for creating diverse agents using a role file framework; and long-term memory and context-aware memory management capabilities through an advanced retrieval-augmented generation system (RAG). In addition, the Eliza framework also provides smooth platform integration, which can be reliably connected with Discord, X, and other social media platforms.
Eliza is an excellent choice for communication and media capabilities of AI agents. On the communication side, the framework supports integration with Discord's voice channel feature, X-features, Telegram, and direct API access for custom use cases. On the other hand, the framework's media processing capabilities have been extended to PDF document reading and analysis, link content extraction and summarization, audio transcription, video content processing, image analysis, and conversation summarization, which can effectively handle a variety of media inputs and outputs.
Eliza provides flexible AI model support, including local reasoning using open source models, cloud-based reasoning through default configurations such as OpenAI and Nous Hermes Llama 3.1B, and supports integration with Claude to handle complex queries. Eliza adopts a modular architecture, has a wide range of action systems, custom client support, and a comprehensive API, ensuring scalability and adaptability across applications.
Eliza's use cases cover multiple areas, such as AI assistants related to customer support, community management, and personal tasks; social media roles such as automatic content creators and brand representatives; it can also serve as a knowledge worker, playing roles such as research assistants, content analysts, and document processors; and interactive roles in the form of role-playing robots, educational mentors, and entertainment agents.
Eliza's architecture is built around an agent runtime that seamlessly integrates with the actor system (supported by model providers), the memory manager (connected to the database), and the action system (linked to the platform client). Unique features of the framework include a plugin system that allows modular functionality extensions, support for multimodal interactions such as voice, text, and media, and compatibility with leading AI models such as Llama, GPT-4, and Claude. With its versatility and powerful design, Eliza has become a powerful tool for developing AI applications across domains.
G.A.M.E
G.A.M.E. was developed by the official Virtuals team. Its full name is "The Generative Autonomous Multimodal Entities Framework". The framework aims to provide developers with an application programming interface (API) and a software development kit (SDK) so that they can experiment with AI agents. The framework provides a structured approach to managing the behavior, decision-making, and learning process 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 the agent to obtain agent behavior.
The "Perception Subsystem" starts a conversation by specifying parameters such as the session ID, agent ID, user, and other relevant details. It synthesizes incoming messages into a format suitable for the "Strategic Planning Engine" and acts as a sensory input mechanism for the AI agent, whether in the form of dialogue or reaction. The core here is the "Dialogue Processing Module", which is responsible for processing messages and responses from the agent and collaborates with the "Perception Subsystem" to effectively interpret and respond to input.
The Strategic Planning Engine works in conjunction with the Dialogue Processing Module and the On-Chain Wallet Operator to generate responses and plans. The engine operates on two levels: as a high-level planner that creates broad strategies based on context or goals; and as a low-level strategy 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 critical component is the “world context”, which references the environment, world information, and game state to provide the necessary context for the agent’s decision making. Additionally, the “agent repository” is used to store long-term attributes such as goals, reflections, experience, and personality, which together shape the agent’s behavior and decision-making process. The framework uses “short-term working memory” and “long-term memory processors” – short-term memory retains relevant information about previous actions, outcomes, and current plans; in contrast, long-term memory processors extract key information based on criteria such as importance, recency, and relevance. This memory stores knowledge about the agent’s experience, reflections, dynamic personality, world context, and working memory to enhance decision making and provide a foundation for learning.
To add to the layout, the “learning module” takes 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 to enhance the AI agent’s learning and improve its planning and decision-making capabilities.
The workflow starts with developers interacting through an agent-prompted interface; the “perception subsystem” processes the input and forwards it to the “dialogue processing module,” which manages the interaction logic; then, based on this information, the “strategic planning engine” develops and executes plans using high-level strategies and detailed action plans.
Data from the "world context" and "agent library" inform these processes, while working memory keeps track of immediate tasks. Meanwhile, a "long-term memory processor" stores and retrieves knowledge over time. A "learning module" analyzes the results and incorporates new knowledge into the system, allowing the agent's behavior and interactions to continuously improve.
Rig
Rig is an open source Rust-based framework designed to simplify 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 stores, including MongoDB and Neo4j. The framework's modular architecture has core components such as "provider abstraction layer", "vector storage integration", and "proxy system" to facilitate seamless interaction of LLM.
Rig's primary audience includes developers building AI/ML applications with Rust, and secondary audiences include organizations seeking to integrate multiple LLM providers and vector storage into their Rust applications. The repository is organized using a workspace-based structure and contains multiple crates, enabling scalability and efficient project management. Rig's main features include the "Provider Abstraction Layer", which standardizes the APIs used to complete and embed LLM providers through consistent error handling; the "Vector Storage Integration" component provides an abstract interface for multiple backends and supports vector similarity searches; the "Proxy System" simplifies LLM interactions and supports retrieval enhancement generation (RAG) and tool integration. In addition, the embedding framework provides batch processing capabilities and type-safe embedding operations.
Rig leverages several technical advantages to ensure reliability and performance. Asynchronous operations leverage Rust's asynchronous runtime to efficiently handle large numbers of concurrent requests; the framework's inherent error handling mechanism improves resilience to AI provider or database operation failures; type safety prevents compile-time errors, thereby improving code maintainability; efficient serialization and deserialization processes help process data in formats such as JSON, which is critical for communication and storage of AI services; detailed logging and instrumentation further help debug and monitor applications.
The workflow in Rig starts with a client initiating a request, which flows through the "provider abstraction layer" to interact with the corresponding LLM model; the data is then processed by the core layer, where the agent can use tools or access the vector store to obtain context; the response is generated and refined through complex workflows such as RAG, which includes document retrieval and context understanding, and then returned to the client. The system integrates with multiple LLM providers and vector stores, and can adapt to changes in model availability or performance.
Rig's use cases are diverse and include question answering systems that retrieve relevant documents to provide accurate responses, document search and retrieval for efficient content discovery, and chatbots or virtual assistants that provide context-aware interactions for customer service or education. It also supports content generation, 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 using OpenAI or Anthropic LLM. ZerePy is derived from a modular version of the Zerebro backend, allowing developers to launch agents with functionality similar to that of the Zerebro core. While the framework provides a foundation for the deployment of agents, models must be fine-tuned in order to produce creative outputs. ZerePy simplifies the development and deployment of personalized AI agents, especially for content creation on social platforms, promoting an AI creative ecosystem targeting art and decentralized applications.
Built in Python, the framework emphasizes the autonomy of agents and focuses on the generation of creative outputs, which is consistent with Eliza's architecture + partnership. Its modular design supports memory system integration and facilitates the deployment of agents on social platforms. Its main features include a command line interface for agent management, integration with X, support for OpenAI and Anthropic LLM, and a modular connection system for enhanced functionality.
ZerePy's use cases include social media automation, where users can deploy AI agents to post, reply, like, and forward, thereby increasing platform engagement. In addition, it is also suitable for content creation in areas such as music, memos, and NFTs, and is an important tool for digital art and blockchain-based content platforms.
Horizontal comparison
In our view, each of the above frameworks offers a unique approach to AI development, catering to specific needs and environments, which makes the debate no longer limited to whether these frameworks are competitors, but rather focuses on whether each framework provides unique utility and value.
Eliza stands out for its user-friendly interface, especially for developers familiar with JavaScript and Node.js environments. Its comprehensive documentation helps to set up AI agents on various platforms, and although its rich feature set may present a moderate learning curve, thanks to its use of TypeScript, Eliza is well suited for building agents embedded in the network, as most of the front-end network infrastructure is built in 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 for memory management makes it particularly suitable for building AI assistants of the type of 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 constitute a learning curve for developers.
G.A.M.E is designed for game developers and provides a low-code or no-code interface through an API, making it accessible to users with less technical skills in the gaming field. However, its focus on game development and blockchain integration may have 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 and the additional complexity of blockchain integration.
Rig uses the Rust language, which may not be very user-friendly due to the complexity of the language, which brings great challenges to learning, but it can provide intuitive interactions for those who are proficient in system programming. Compared with TypeScript, Rust itself is known for its performance and memory safety. It has strict compile-time checking and zero-cost abstractions, which are necessary to run complex artificial intelligence algorithms. The efficiency and low control characteristics of the language make it ideal for resource-intensive AI applications. The framework adopts a modular and extensible design to provide high-performance solutions, which is very suitable for enterprise applications. However, for developers who are not familiar with the Rust language, using Rust will bring a steep learning curve.
ZerePy uses the Python language, which provides higher usability for creative AI tasks. For Python developers, especially those with AI/ML backgrounds, the learning curve is low, and due to the popularity of ZEREBRO, there is strong community support. ZerePy excels in creative AI applications such as NFT, and the framework also positions itself as a powerful tool in the field of digital media and art. Although it excels in creativity, its application range is relatively narrow compared to other frameworks.
In terms of scalability, the comparison of the four major frameworks is as follows.
Eliza has made great progress since the V2 update, introducing a unified message line and an extensible core framework to achieve efficient cross-platform management. However, if not optimized, managing this multi-platform interaction may bring scalability challenges.
G.A.M.E excels at the real-time processing required for games, and its scalability can be managed through efficient algorithms and underlying blockchain distributed systems, but may be constrained by the limitations of specific game engines or blockchain networks.
The Rig framework can take advantage of Rust's performance to achieve better scalability and is naturally designed for high-throughput applications, which may be particularly effective for enterprise-level deployments, but this may mean that a complex setup is required to achieve true scalability.
ZerePy's scalability is targeted at creative outputs and is supported by community contributions, but the framework's focus may limit its applicability to broader AI contexts, and its scalability may be tested by the diversity of creative tasks rather than the number of users.
In terms of applicability, Eliza leads the pack with its plugin system and cross-platform compatibility, followed by G.A.M.E. in gaming environments and Rig for complex AI tasks. ZerePy shows high adaptability in creative fields, but is less applicable to a wider range of AI applications.
In terms of performance, the test results of the four major frameworks are as follows.
Eliza is optimized for fast interactions on social media, but performance may vary when handling more complex computing tasks.
G.A.M.E focuses on high-performance real-time interactions in game scenarios, leveraging efficient decision-making processes and possible blockchains for decentralized AI operations.
Rig is based on Rust and provides excellent performance for high-performance computing tasks, making it suitable for enterprise applications where computing efficiency is critical.
ZerePy’s performance is targeted at creative content creation, and its metrics center on the efficiency and quality of content generation, which may not be very general outside of the creative field.
Combining the above comprehensive analysis of advantages and disadvantages, Eliza provides better flexibility and scalability. The plug-in system and role configuration make it highly adaptable, which is conducive to cross-platform social AI interaction; G.A.M.E can provide unique real-time interaction capabilities in game scenarios and provides novel AI participation through blockchain integration; Rig's advantages lie in its performance and scalability, which is suitable for enterprise-level AI tasks, and focuses on code simplicity and modularity to ensure the long-term healthy development of the project; Zerepy is good at cultivating creativity, leading in AI applications for digital art, and supported by a vibrant community-driven development model.
In summary, each framework has its limitations. Eliza is still in its early stages, has potential stability issues, and has a long learning curve for new developers; G.A.M.E.'s niche focus may limit its wider application, and the introduction of blockchain will also increase complexity; Rig's learning curve is steeper due to the complexity of the Rust language, which may discourage some developers; Zerepy's narrow focus on creative output may limit its application in other AI fields.
Core comparison items
Rig（ARC）
Language: Rust, with a focus on safety and performance.
Use cases: Focused on efficiency and scalability, it is ideal for enterprise-level AI applications.
Community: Less community driven and more focused on technical developers.
Eliza (AI16Z)
Language: TypeScript, emphasizing Web3 flexibility and community participation.
Use Cases: Designed for social interactions, DAOs, and transactions, with a special emphasis on multi-agent systems.
Community: Highly community driven, with extensive connections to GitHub.
ZerePy (CEREBRO):
Language: Python, which is more accessible to a wider group of AI developers.
Use Cases: Good 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）：
Focus: Autonomous, adaptive AI agents that evolve based on interactions in virtual environments.
Use Cases: Best used in scenarios where the agent needs to learn and adapt, such as games or virtual worlds.
Community: Innovative, but still figuring out its position within the competition.
Github data growth
The above chart shows the changes in the star data of these frameworks on GitHub since their launch. In general, GitHub stars can be used as an indicator of community interest, project popularity, and project perceived value.
Eliza (red line): The chart shows significant and steady growth in the number of stars for this framework, starting from a low base in July and surging in late November, now reaching 6,100 stars. This shows the rapid surge of interest around the framework, attracting the attention of developers. The exponential growth shows that Eliza has gained huge traction due to its features, updates and community participation. Its popularity far exceeds that of other products, which shows that it has strong support from the community. In the artificial intelligence community have broader applicability or interest.
Rig (blue line): Rig is the oldest of the four frameworks. Its star growth is not large, but very stable, and has increased significantly in the last month. Its total number of stars has reached 1,700, but it is still on an upward trajectory. The steady accumulation of attention is due to continuous development, updates, and a growing user base. This may reflect that Rig is a framework that is still accumulating reputation.
ZerePy (yellow line): ZerePy was just launched a few days ago and has grown to 181 stars. It should be emphasized that ZerePy needs more development to increase its visibility and adoption, and the cooperation with ai16z may attract more contributors to its code base.
G.A.M.E (green line): This framework has a low number of stars, but it is worth noting that the framework can be directly applied to agents in the Virtual ecosystem through the API, so there is no need to publish on Github. However, although the framework was only publicly available to builders a little over a month ago, there are already more than 200 projects building with G.A.M.E.
Expected upgrades to the AI framework
Eliza's 2.0 version will include integration with the Coinbase Proxy Toolkit. All projects using Eliza will gain support for future native TEEs (Trusted Execution Environments), enabling proxies to run in a secure environment. The Plugin Registry is an upcoming feature of Eliza that allows developers to seamlessly register and integrate plugins.
In addition, Eliza 2.0 will support automated anonymous cross-platform messaging. The Tokenomics white paper, expected to be released on January 1, 2025, will have a positive impact on the AI16Z token that supports the Eliza framework. ai16z plans to continue to strengthen the practicality of the framework and leverage the efforts of its major contributors to bring in high-quality talent.
The G.A.M.E framework provides code-free integration for agents, making it possible to use both G.A.M.E and Eliza in a single project, each serving a specific use case. This approach is expected to attract builders who focus on business logic rather than technical complexity. Although the framework has only been publicly available for more than 30 days, it has made substantial progress as the team works hard to attract support from more contributors. It is expected that every project launched on VirtuaI will adopt G.A.M.E.
The Rig framework powered by the ARC token has significant potential, although the growth of the framework is in its early stages and the project contract program to drive Rig adoption has only been live for a few days. However, high-quality projects paired with ARC are expected to emerge soon, similar to Virtual Flywheel but focused on Solana. The Rig team is optimistic about cooperation with Solana and positions ARC as Solana's Virtual. Notably, the team not only incentivizes new projects launched using Rig, but also incentivizes developers to enhance the Rig framework itself.
Zerepy is a newly launched framework that is gaining a lot of traction due to its collaboration with ai16z (Eliza framework), which has attracted contributors from Eliza who are actively working to improve the framework. Zerepy enjoys avid support driven by the ZEREBRO community and is opening up new opportunities for Python developers who were previously underserved in the competitive AI infrastructure space. The framework is expected to play a major role in the creative side of AI.