Original text: Deep Value Memetics; Translator: Azuma
Key points overview
In this report, we discuss the development landscape of several mainstream frameworks in the Crypto & AI field. We will examine the four major frameworks — Eliza (AI16Z), G.A.M.E (GAME), Rig (ARC), and ZerePy (ZEREBRO), analyzing their technical differences and development potential.
In the past week, we analyzed and tested the above four frameworks, and the summary of conclusions is as follows.
We believe Eliza (approximately 60% market share, valued at about $900 million when the original author wrote, approximately $1.4 billion at the time of publication) 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, 1,800 forks, and over 6,000 stars on GitHub, making it one of the most popular software libraries on GitHub.
G.A.M.E (approximately 20% market share, valued at about $300 million when the original author wrote, approximately $257 million at the time of publication) has had a very smooth development so far and is experiencing rapid adoption, as noted in an earlier announcement from the Virtuals Protocol, which indicates that over 200 projects have been built based on G.A.M.E, with daily request counts exceeding 150,000 and a weekly growth rate exceeding 200%. G.A.M.E will continue to benefit from the explosion of VIRTUAL and has the potential to become one of the biggest winners in that ecosystem.
Rig (approximately 15% market share, valued at about $160 million when the original author wrote, approximately $279 million at the time of publication) features a notable and user-friendly modular design, with potential to dominate in the Solana ecosystem (RUST).
Zerepy (approximately 5% market share, valued at about $300 million when the original author wrote, approximately $424 million at the time of publication) is a more niche application, specific to a fervent ZEREBRO community, and its recent cooperation with the ai16z community may yield some synergistic effects.
In the above statistics, 'market share' is calculated considering market capitalization, development records, and the breadth of the underlying operating system terminal markets comprehensively.
We believe that AI frameworks will become the fastest-growing sector this cycle, with the current total market cap of approximately $1.7 billion poised to easily grow to $20 billion, which may still be conservative compared to the peak valuations of Layer 1 in 2021 — when many individual projects were valued at over $20 billion. Although the aforementioned frameworks serve different end markets (chains/ecosystems), given our belief that this sector will grow overall, adopting a market cap-weighted approach may be relatively prudent.
The 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 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, their technical architectures, algorithms, and unique features with potential use cases. We will then compare each framework based on usability, scalability, adaptability, and performance, while discussing their strengths and limitations.
Eliza
Eliza is an open-source multi-agent simulation framework developed by ai16z, aimed at creating, deploying, and managing autonomous AI agents. Developed in TypeScript, it provides 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: supporting the simultaneous deployment and management of multiple unique AI personalities through a multi-agent architecture; creating a diverse agent role system using a role file framework; providing long-term memory and context-aware memory management capabilities through advanced retrieval-augmented generation systems (RAG). Furthermore, the Eliza framework offers seamless platform integration, allowing 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 functionalities, Telegram, and direct API access for customized use cases. On the other hand, the framework's media processing capabilities have expanded to include reading and analyzing PDF documents, content extraction and summarization from links, audio transcription, video content processing, image analysis, and dialogue summarization, effectively handling diverse media inputs and outputs.
Eliza offers flexible AI model support, allowing for local inference using open-source models, cloud-based inference using default configurations from OpenAI and Nous Hermes Llama 3.1 B, and supports integration with Claude for handling complex queries. Eliza adopts a modular architecture with a wide action system, custom client support, and comprehensive APIs, ensuring scalability and adaptability across applications.
Eliza's use cases span multiple fields, such as AI assistants related to customer support, community management, and personal tasks; automated content creators and brand representatives in social media roles; it can also serve as a knowledge worker, taking on roles such as research assistant, content analyst, and document processor; as well as interactive roles in the form of role-playing bots, educational mentors, and agent representatives.
Eliza's architecture is built around an agent runtime that integrates seamlessly with a role system (supported by model providers), a memory manager (connected to a database), and an action system (linked to platform clients). Unique features of this framework include a plugin system that allows for modular functionality expansion, support for multimodal interactions including voice, text, and media, and compatibility with leading AI models such as Llama, GPT-4, and Claude. With its versatility 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, officially known as 'The Generative Autonomous Multimodal Entities Framework,' which aims to provide developers with APIs and SDKs to experiment with AI agents. This framework offers a structured approach to managing AI agent behavior, decision-making, and learning processes.
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 to obtain agent behavior.
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 the AI agent, whether in the form of dialogue or reactions. The 'Dialogue Processing Module' is key here, responsible for handling messages and responses from the agent, 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, creating broad strategies based on context or goals; and as a low-level strategy, translating these strategies into executable policies, further divided into action planners (for specifying tasks) and plan executors (for executing tasks).
A separate but crucial component is the 'World Context,' which refers to the environment, world information, and game state, providing 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 personality, which collectively shape the agent's behavior and decision-making process. The framework employs a 'short-term working memory' and a 'long-term memory processor' — the 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 importance, recency, and relevance. This memory stores knowledge about the agent's experiences, reflections, dynamic personality, 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 through the interface on actions, game states, and sensory data to enhance the learning of the AI agent and improve its 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 based on this information using advanced strategies and detailed action planning.
Data from the 'World Context' and 'Agent Library' inform these processes, while working memory tracks immediate tasks. The 'Long-term Memory Processor' stores and retrieves knowledge over time. The 'Learning Module' analyzes results and integrates new knowledge into the system, allowing for continuous improvement in the agent's behavior and interactions.
Rig
Rig is an open-source framework based on Rust, designed to simplify the development of applications using large language models (LLMs). It provides a unified interface for interacting with multiple LLM providers, such as OpenAI and Anthropic, and supports various vector storage solutions, including MongoDB and Neo4j. The modular architecture of the framework features core components such as the 'Provider Abstraction Layer,' 'Vector Storage Integration,' and 'Agent System,' facilitating seamless interaction with LLMs.
Rig's primary audience includes developers building AI/ML applications using Rust, with a secondary audience of organizations seeking to integrate multiple LLM providers and vector storage into their Rust applications. The repository is organized using a workspace-based structure, containing multiple crates that achieve scalability and efficient project management. Rig's main features include the 'Provider Abstraction Layer,' which standardizes API completion and embedding of 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' streamlines LLM interactions, supporting retrieval-augmented generation (RAG) and tool integration. Additionally, the embedding framework offers 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 number of concurrent requests; the framework's inherent error handling mechanisms enhance recovery from AI provider or database operation failures; type safety prevents compilation errors, improving code maintainability; efficient serialization and deserialization processes aid in handling data in formats like JSON, which is crucial for communication and storage of AI services; detailed logging and instrumentation further assist in debugging and monitoring applications.
The workflow in Rig starts with the client initiating a request, which flows through the 'Provider Abstraction Layer' to interact with the relevant LLM model; then, the 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 such as RAG, including document retrieval and context understanding, before being returned to the client. The system integrates multiple LLM providers and vector storage to adapt to changes in model availability or performance.
The use cases of Rig are diverse, including retrieval of relevant documents to provide accurate responses in question-answering systems, 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 using OpenAI or Anthropic LLM. ZerePy originates from a modular version of the Zerebro backend, allowing developers to launch agents with similar functionalities to Zerebro's core features. While this framework provides a foundation for agent deployment, fine-tuning of the model is necessary to generate creative outputs. ZerePy simplifies the development and deployment of personalized AI agents, particularly for content creation on social platforms, fostering an AI creative ecosystem aimed at art and decentralized applications.
This framework is built using Python, emphasizing agent autonomy and focusing on generating creative outputs, consistent with Eliza's architecture + partnerships. Its modular design supports memory system integration, facilitating 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 LLMs, and a modular connection system for enhanced functionalities.
ZerePy's use cases cover social media automation, enabling users to deploy AI agents for posting, replying, liking, and sharing, thereby enhancing platform engagement. Additionally, it is applicable 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 view, each of the above frameworks offers a unique approach to AI development, catering to specific needs and environments, which shifts the debate from whether these frameworks compete with each other to whether each framework can provide unique utility and value.
Eliza stands out with its user-friendly interface, especially suitable for developers familiar with JavaScript and Node.js environments. Its comprehensive documentation helps set up AI agents across various platforms, and although its rich feature set may present a moderate learning curve, Eliza is very suitable for building agents embedded in the web since most frontend web infrastructure is built using TypeScript. The framework is known for its multi-agent architecture, capable of deploying diverse AI personality agents across platforms like Discord, X, and Telegram. Its advanced RAG system for memory management makes it particularly well-suited for building AI assistants for 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, which may pose a learning curve for developers.
G.A.M.E is designed specifically for game developers, providing a low-code or no-code interface via API, making it accessible for users with lower technical proficiency 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 and the added complexity of blockchain integration.
Rig may be less user-friendly due to the complexity of the Rust language, presenting significant challenges for learning, but it can provide intuitive interaction 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 efficiency and low-level control characteristics of this language make it an ideal choice for resource-intensive AI applications. The framework adopts a modular and scalable design to provide high-performance solutions, making it very suitable for enterprise applications. However, for developers unfamiliar with the Rust language, there will be a steep learning curve when using Rust.
ZerePy uses Python, providing higher accessibility for creative AI tasks. For Python developers, especially those with an AI/ML background, the learning curve is lower, and strong community support is available due to ZEREBRO's popularity. ZerePy excels in creative AI applications such as NFTs, positioning itself as a powerful tool in the digital media and arts space. While it performs exceptionally in creative aspects, 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 significant progress following its V2 update, introducing a unified messaging line and an expandable core framework for efficient cross-platform management. However, without optimization, managing such multi-platform interactions may present scalability challenges.
G.A.M.E excels in real-time processing required for gaming, and its scalability can be managed through efficient algorithms and potential blockchain distributed systems, although it may be constrained by specific game engines or blockchain networks.
The Rig framework can leverage Rust's performance advantages 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 focused on creative output and supported by community contributions, but the framework's emphasis may limit its application in broader AI environments, as its scalability may be tested more by the diversity of creative tasks than by user numbers.
In terms of applicability, Eliza leads with its plugin system and cross-platform compatibility, followed by G.A.M.E in gaming environments and Rig for handling complex AI tasks. ZerePy has shown high adaptability in creative fields but is less applicable in the broader AI application domain.
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 its performance may vary when handling more complex computational tasks.
G.A.M.E focuses on high-performance real-time interactions in gaming scenarios, utilizing efficient decision-making processes and potential blockchain for decentralized AI operations.
Rig, based on Rust, offers excellent performance for high-performance computing tasks, making it suitable for enterprise applications where computational efficiency is critical.
ZerePy's performance is tailored for the creation of creative content, with its metrics centered on the efficiency and quality of content generation, which may not be as generalizable outside the creative domain.
Considering the comprehensive analysis of the above strengths and weaknesses, Eliza offers better flexibility and scalability, with its plugin system and role configurations providing strong adaptability, conducive to cross-platform social AI interactions; G.A.M.E offers unique real-time interaction capabilities in gaming scenarios and provides novel AI involvement through blockchain integration; Rig's strengths lie in its performance and scalability, making it suitable for enterprise-level AI tasks, while focusing on code simplicity and modularity to ensure the long-term health of projects; Zerepy excels in nurturing creativity, leading in the application of AI in 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 longer learning curve for new developers; G.A.M.E's niche focus may limit its broader applications, and the introduction of blockchain may add complexity; Rig's steep learning curve due to the complexity of the Rust language may deter some developers; Zerepy's narrow focus on creative output may restrict its application in other AI domains.
Core comparison items overview
Rig (ARC):
Language: Rust, focusing on safety and performance.
Use case: Emphasizing efficiency and scalability, making it an ideal choice for enterprise-level AI applications.
Community: Less community-driven, focusing more on technical developers.
Eliza (AI16Z):
Language: TypeScript, emphasizing flexibility and community engagement in Web3.
Use case: Specifically designed for social interaction, DAOs, and transactions, with a strong emphasis on multi-agent systems.
Community: Highly community-driven, with extensive ties to GitHub.
ZerePy (ZEREBRO):
Language: Python, more easily accepted by a broader group of AI developers.
Use case: 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):
Focus: Autonomous, adaptive AI agents that can evolve based on interactions in virtual environments.
Use case: Best suited for scenarios where agents need to learn and adapt, such as games or virtual worlds.
Community: Innovative but still finding its niche in competition.
GitHub data growth status
The above chart 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 projects.
Eliza (red line): The chart shows significant and stable growth in the number of stars for this framework, starting from a low base in July, surging dramatically in late November, now reaching 6,100 stars. This indicates a rapid increase in interest around this framework, attracting developer attention. The exponential growth suggests that Eliza has gained immense traction due to its features, updates, and community involvement, far surpassing other products, indicating strong community support and broader applicability or interest in the AI community.
Rig (blue line): Rig is the most 'established' among the four major frameworks, showing modest but stable star growth, with a noticeable increase in the last month. Its total number of stars has reached 1,700, but it is still on an upward trajectory. The stable accumulation of attention is attributed 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 was just launched a few days ago, and the number of stars has already grown to 181. It is important to emphasize that ZerePy needs more development to enhance its visibility and adoption rate, and cooperation with ai16z may attract more contributors to its codebase.
G.A.M.E (green line): This framework has relatively few stars, but it is noteworthy that it can be directly applied to agents in the Virtual ecosystem via API, thus not requiring publication on GitHub. However, although this framework was only publicly available for builders a little over a month ago, there are already over 200 projects using G.A.M.E for their builds.
Expectations for upgrades of AI frameworks
Eliza's 2.0 version will include integration with the Coinbase agent toolkit. All projects using Eliza will gain support for future native TEE (Trusted Execution Environment), allowing agents to operate in a secure environment. A plugin registry is a forthcoming feature of Eliza, enabling developers to seamlessly register and integrate plugins.
Additionally, Eliza 2.0 will support automated anonymous cross-platform messaging. The Tokenomics whitepaper, expected to be released on January 1, 2025 (related proposals have been published), will positively impact the AI16Z tokens supporting the Eliza framework. ai16z plans to continue enhancing the framework’s usability and attract high-quality talent through the efforts of its main contributors.
The G.A.M.E framework provides agents with no-code integration, allowing G.A.M.E and Eliza to be used simultaneously in a single project, each serving specific use cases. This approach is expected to attract builders focused on business logic rather than technical complexities. 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 contributors. It is expected that every project launched on VirtualI will adopt G.A.M.E.
The Rig framework, powered by the ARC token, has significant potential, although its growth is in the early stages, and the project contract plan driving Rig adoption has only been live for a few days. However, high-quality projects paired with ARC are expected to emerge soon, similar to the Virtual flywheel, but focused on Solana. The Rig team is optimistic about collaboration with Solana, positioning ARC as Solana's Virtual. Notably, the team incentivizes not only new projects launched using Rig but also encourages developers to enhance the Rig framework itself.
Zerepy is a newly launched framework that is gaining significant attention due to its collaboration with ai16z (Eliza framework). This framework has attracted contributors from Eliza who are actively working to improve it. Zerepy enjoys enthusiastic support from the ZEREBRO community and is opening new opportunities for Python developers who previously lacked space in the competitive AI infrastructure field. The framework is expected to play an important role in the creative aspects of AI.