The ebb of speculation How will the development of the popular AI agent framework Web3 be Who will dominate 2025

Source: Blockchain Knight

In early 2025, the Crypto industry ushered in a wave of social platform automation frenzy, with AI agent frameworks undoubtedly being the key driver behind the scenes. From automatically managing social content to generating personalized NFTs, these technologies are redefining the way users interact with blockchain.

This article will delve into the six major AI agent frameworks - ElizaOS, G.A.M.E, ARC, ZEREBRO, REI, and Swarms, and how they are seizing the opportunity in this wave of Crypto industry frenzy with their unique technological advantages, as well as the latest developments and future directions of these teams after experiencing the speculative frenzy.

1、ElizaOS

Project Introduction:

ElizaOS is an open-source framework designed to create, deploy, and manage autonomous AI agents. Built using TypeScript, it provides a modular, scalable platform that allows developers to create intelligent agents that can interact across multiple platforms such as Discord, Twitter, and Telegram while maintaining consistent personality and knowledge.

Technical Advantages:

The design based on TypeScript reduces the learning curve for developers, making it easier to get started quickly and with a higher maturity of the ecosystem and developer adoption compared to frameworks using Rust (such as ARC) or Python (such as ZEREBRO).

Github stars count:

14.7K

Latest developments:

• Core functionality and design philosophy update: The documents and white paper released in January emphasized the five core components of ElizaOS: Agents, Character Files, Providers, Actions, and Evaluators, which make up a powerful, controllable framework tailored for Web3.
• MultiversX AI Agent Toolkit: MultiversX announced the launch of the AI agent toolkit based on ElizaOS in mid to late February 2025, through X. This open-source toolkit allows developers to build custom AI agents in minutes, supporting over 250 models, including the new DeepSeek model.
• Integration with Sei Network: ElizaOS recently integrated with Sei Network, which is touted as one of the fastest blockchains, which enables AI agents to run autonomously on Sei to perform tasks such as crypto trading and asset management.
• ElizaOS version v0.25.8 released: ElizaOS has just released its latest version v0.25.8, this update removes all plugins from the main repository, reducing redundancy and simplifying the installation process - a major improvement for user experience. New features include support for more large language models (LLM), such as models from NEAR AI and Secret Network, as well as a dynamic plugin system to enhance flexibility.

Future Expectations:

With the successful landing of plugin separation and multi-model support in version v0.25.8, future versions of ElizaOS may introduce more powerful cross-chain compatibility, not limited to existing integrations, to support more complex financial, gaming, and social use cases. Its open-source nature and community-driven plugin ecosystem are expected to drive this process, with developers potentially contributing more specialized toolkits, such as dedicated agents for 3D content generation for the metaverse or decentralized identity management.

In terms of functionality, ElizaOS may deepen its multimodal capabilities, integrate text, image, and audio processing more seamlessly, and may even launch a native AI-powered real-time decision-making engine for scenarios such as supply chain management or dynamic NFT marketplaces.

二、G.A.M.E

Project Introduction:

G.A.M.E is an AI agent framework developed by Virtuals Protocol, a decentralized network based on Base. It is committed to enabling autonomous AI agents to run on multiple platforms, integrate with blockchain technology, and create a tokenized, agent-driven economic system. G.A.M.E has attracted attention due to its convenient SDK (Software Development Kit) and enhanced agent capabilities, contributing to the Virtuals ecosystem, which has a total market value of $6 billion and supports multiple high-value AI agent projects.

Technical Advantages:

Provides a low-code toolkit that is suitable for non-technical users to quickly deploy agents, compared to frameworks that require programming skills such as ElizaOS or ARC, G.A.M.E significantly reduces the learning curve.

Number of Github Stars:

131

Latest development:

• Virtuals ecosystem buyback and burn plan: Virtuals Protocol announced a buyback and burn plan in mid-January, which had a significant impact on the G.A.M.E. framework. Virtuals used 13 million VIRTUAL tokens (11.7 million US dollars) to repurchase and burn 25 AI agent tokens, including 1.6 million GAME tokens.
• GOAT SDK integration: In mid to late January, G.A.M.E announced the integration with GOAT SDK, unlocking '200+ on-chain actions' for G.A.M.E agents. This collaboration is described as 'changing the rules of the game,' enhancing agents' blockchain interactivity.
• DeepSeek Integration: In mid-February, G.A.M.E announced the integration of the high-performance large-scale language model DeepSeek into the G.A.M.E framework. The addition of DeepSeek enhances the inference and conversational capabilities of G.A.M.E agents. This upgrade may improve the agent's ability to handle cross-platform complex tasks, becoming a key differentiating advantage for G.A.M.E.
• Multi-platform autonomy upgrade: In mid to late February, G.A.M.E released a major upgrade to the SDK, giving AI agents the ability to autonomously operate on X, Discord, Telegram, and Farcaster, making them more than just plugins, but truly multi-platform autonomous entities. This update transitions from static plugins to dynamic cross-platform agent coordination - for example, an agent can initiate tasks on Telegram and complete them on Discord.

Future Expectations:

Based on its SDK, which has seen astonishing growth in the past three months, future versions may further optimize the development experience and introduce a more powerful toolset, such as built-in smart contract templates or real-time data analysis modules. On the technical side, G.A.M.E may deepen its multi-platform autonomy functionality, surpassing current X, Discord, Telegram, and Farcaster integrations, and expanding to a wider range of decentralized social networks. In addition, the continuous integration of high-performance language models like DeepSeek may drive breakthroughs for G.A.M.E agents in natural language processing and decision reasoning, making them suitable for a broader range of scenarios, such as automated customer support or on-chain governance.

Three, ARC (RIG)

Project Introduction:

RIG is an open-source AI proxy framework developed by ARC and written in Rust. It aims to simplify the creation of autonomous AI agents by providing a modular architecture that supports multiple large language models (LLMs), vector databases for memory management, and scalable tool integration.

!

Technical advantages:

Based on Rust's memory safety and zero-cost abstraction features, RIG performs well in resource-intensive tasks, making it more suitable for enterprise applications.

Github stars count:

3.1K

Latest developments:

• The GitHub repository launch and documentation: RIG's official GitHub repository was publicly released at the end of last December, with basic documentation outlining installation instructions, supported models, and a simple 'Hello World' proxy example.
• Support for mainstream models and tools: In January of this year, RIG consolidated its support for mainstream LLMs, including standard utilities (e.g., web scraping, file I/O), and more.
• Agent Launchpad FORGE: In mid-February, ARC launched the 'ARC FORGE,' a Launchpad for agent-driven tokens, and announced the first project AskJimmy, an AI-driven trading platform. FORGE uses the RIG framework for AI agents to manage token issuance, integrating with blockchain for decentralized trading.

Future Expectations:

Although RIG's Rust features limit beginners from entering, its high performance and security will attract professional developers, especially in scenarios requiring low latency and high throughput, such as GameFi or DeFi protocols. In the future, ARC may reduce the learning curve and accelerate the development of community plug-in ecosystem, for example, with richer documentation, tutorials, and pre-built templates, dedicated adapters for Solana or Base blockchains.

Four, ZEREBRO (ZerePy)

Project Introduction:

ZerePy is a Python framework developed based on Zerebro's back-end technology, launched by the Zerebro team in collaboration with ai16z, and is known as "the first Python-based AI proxy framework in the Crypto field". ZerePy takes Zerebro's core functionality, such as content generation and social platform interaction, and encapsulates it into a toolset that developers can use directly.

Technical Advantages:

The ZerePy framework excels at art generation (e.g., NFTs, music), is unique in the entertainment and social media space compared to more general-purpose frameworks, and its Python-based architecture is very friendly to AI/ML developers.

Github Stars count:

553

Latest development:

• Integration with the Zerebro ecosystem and Zentients Launchpad: In early January this year, ZerePy was linked to the tokenized ecosystem of Zerebro, expanding its utility beyond being an independent framework.
• Increased community interest: Early adoption focused on lightweight applications (e.g., X Automation, Content Creation), and ZerePy's Python foundation appealed to a wider audience than Rust or TypeScript frameworks.
• TEE in ZerePy: In mid to late January, the upgraded ZerePy can run in the trusted execution environment (TEE) to achieve secure cloud deployment.

Future Expectations:

ZerePy's Python base provides extensive community support and ecosystem compatibility, making it a preferred tool for Python developers to build Web3-driven AI agents, especially in the fields of social media automation and decentralized creative applications. Within the Zerebro ecosystem, the development of ZerePy may be deeply integrated with Zentients Launchpad, supporting the incubation and deployment of several new agent projects.

5. REI

Project Introduction:

REI is an AI proxy framework that aims to bridge the gap between AI and blockchain and solve technical incompatibilities such as conflicting computing resources and mismatched data structures. REI uses a modular architecture that leverages an Oracle Bridge to connect on-chain and off-chain data, enabling AI agents to analyze and make decisions in real-time in a decentralized environment.

Technological Advantages:

Focusing on the design of complex distributed architectures, it is more suitable for developers who need advanced customization than easy-to-use frameworks such as G.A.M.E.

Github stars count:

No public link available

Latest Development:

• Integrated with the Base blockchain: In early January, REI integrated with Base to improve scalability and reduce Gas costs. Base's low-cost, high-throughput environment complements REI's resource-intensive AI operations. The oracle bridge connects Base's on-chain data to off-chain AI reasoning, enabling agents to adjust DeFi parameters in real-time (such as liquidity pool ratios).
• Dynamic NFT use case demonstration: In mid to late January, a demonstration on X showed that REI agents can dynamically update NFT attributes based on on-chain activities (such as user transaction history), highlighting the practicality of REI.

Future Expectations:

Based on its current oracle bridge and modular proxy system, future versions may further optimize the on-chain/off-chain collaboration efficiency, for example, by integrating more efficient zero-knowledge proofs (ZKPs) or trusted execution environments (TEEs) to enhance privacy protection and computational speed. This will enable the REI proxy to handle more complex workloads, such as dynamic risk management for large-scale DeFi protocols or real-time supply chain optimization. As it integrates successfully with the Base chain, REI may further collaborate with Layer2 ecosystems (such as Arbitrum or Optimism) to leverage low-cost and high-throughput environments, driving the implementation of enterprise-level applications.

Six, Swarms

Project Introduction:

Swarms is an open-source framework for coordinating multiple AI agents, emphasizing modularity, scalability, and lightweight design. Unlike a single-agent system, Swarms implements distributed task execution, specializing in agent collaboration to solve problems—for example, one agent analyzes data, another executes trades, and a third manages output.

Technical Advantages:

Focus on proxy group collaboration, simulating collective intelligence in nature (such as bee colony), it is more efficient in handling complex tasks compared to frameworks that are mainly based on single agents (such as ZEREBRO or G.A.M.E).

Github Stars count:

18.9K

Latest development:

• Market launch on the Swarms platform: In December last year, Swarms launched a market that allows developers to discover and monetize agents, tools, and prompts. The market is integrated with the Swarms SDK, and developers can deploy agents (e.g., for trading or content generation) and earn SWARMS. It supports interaction between agents, forming a group that adapts and improves over time, similar to a natural ecosystem.
• Companies adopt milestones: CryptoSlate reported in January this year that Swarms has deployed over 45 million agents in the financial, insurance, and medical fields to serve top companies.
• Swarms7.2.6 version released: In late February, the Swarms7.2.6 version was released, emphasizing the fixing of multiple errors and the addition of new features. This update enhances agent collaboration through role and improved group architecture (such as RoundRobin, GroupChat, ConcurrentWorkflow, and AgentRearrange).
• Proxy and Multi-proxy API: Swarms recently launched proxy and multi-proxy API, aiming to simplify the integration of group architecture (such as Concurrent, Sequential, HierarchicalSwarm, RoundRobin). These hosted APIs will support various models, enhancing application development capabilities.

Future Expectations:

Swarms' open-source nature and upcoming proxy and multi-broker APIs bode well for the rapid expansion of its developer ecosystem, and in the future, its SDK may fully support cross-platform deployment, leveraging its lightweight design and fault-tolerant mechanism (automatic adaptation after proxy failure) to enable seamless multi-chain operations. In addition, with the improvement of the memory system, the Swarms agent may have long-term contextual memory to support task planning across time dimensions. In terms of community and market influence, its openness and Solana's low-cost advantages will attract more developers, especially in the DeFi and GameFi space.

Summary

With low-code development, high-performance architecture, multimodal capabilities, and seamless integration with blockchain, these AI agent frameworks have successfully met the market's demands for efficiency, creativity, and practicality.

Looking to the future, with the popularization of high-performance language models, the maturity of high-throughput blockchains, and the further expansion of tokenized economies, these frameworks are expected to break through existing boundaries, develop stronger cross-chain compatibility, privacy protection mechanisms, and long-term mission planning capabilities, and promote the deep integration of Web3 in social, gaming, financial, and even real-world applications.

Compared to the development path of traditional AI agents, these agent frameworks rooted in the Web3 direction still have a long way to go. After experiencing the speculative period, these agent development teams need to put more effort into development and business expansion in order to usher in the next boom.