🎉 The #CandyDrop Futures Challenge is live — join now to share a 6 BTC prize pool!
📢 Post your futures trading experience on Gate Square with the event hashtag — $25 × 20 rewards are waiting!
🎁 $500 in futures trial vouchers up for grabs — 20 standout posts will win!
📅 Event Period: August 1, 2025, 15:00 – August 15, 2025, 19:00 (UTC+8)
👉 Event Link: https://www.gate.com/candy-drop/detail/BTC-98
Dare to trade. Dare to win.
AI Agent Framework Eliza upgraded to V2 version, fully reconstructed to enhance performance and scalability.
AI Agent framework Eliza upgraded to V2 version, architecture restructured to improve performance
Recently, the development team of the AI Agent framework Eliza announced that they are working on the V2 version, which is expected to release the alpha test version within 2-3 weeks. This upgrade will involve a comprehensive restructuring of the framework, aimed at enhancing performance and scalability.
The Eliza framework currently consists of the interface layer, core functionality layer, and model layer. The interface layer is responsible for interacting with external platforms such as Discord, Twitter, and Telegram, and provides API interfaces. The core functionality layer includes the memory system, behavior system, and configuration system, which are responsible for storage and retrieval, behavior management, and configuration management, respectively. The model layer supports various large language models, such as OpenAI, Anthropic, and Llama.
The V2 version will be improved in several aspects:
The interface layer introduces a unified message bus, integrating dispersed clients into a unified message processing system, simplifying development and maintenance tasks.
The core functionality layer adds a unified proxy wallet, integrating the existing decentralized wallet configuration, providing multi-chain wallet management, and simplifying cross-chain operations.
Redesign the core interface to make the framework more versatile and extensible, and improve the plugin integration mechanism.
Update the community plugin system, improve plugin management, and achieve 100% test coverage to ensure quality.
The model layer introduces a model registry mechanism that supports dynamic registration and overrides, dividing models into two main categories: LLMs and Embeddings, providing a more flexible calling method.
These improvements make the architecture of Eliza V2 more modular and unified, with clearer interactions between components, laying a solid foundation for future expansion. The release of the new version will also bring new development opportunities for plugins that expand functionalities based on Eliza.