📢 Gate Square Exclusive: #WXTM Creative Contest# Is Now Live!
Celebrate CandyDrop Round 59 featuring MinoTari (WXTM) — compete for a 70,000 WXTM prize pool!
🎯 About MinoTari (WXTM)
Tari is a Rust-based blockchain protocol centered around digital assets.
It empowers creators to build new types of digital experiences and narratives.
With Tari, digitally scarce assets—like collectibles or in-game items—unlock new business opportunities for creators.
🎨 Event Period:
Aug 7, 2025, 09:00 – Aug 12, 2025, 16:00 (UTC)
📌 How to Participate:
Post original content on Gate Square related to WXTM or its
The AI Agent framework Eliza V2 is about to be released with a comprehensive upgrade of its architecture and features.
The upgraded version V2 of the AI Agent framework Eliza is about to be launched.
Recently, the AI Agent framework Eliza of AI16Z is undergoing a major upgrade. The new version V2 is expected to launch the alpha test version in 2-3 weeks, bringing multiple optimizations in architecture and functionality.
The current version of the Eliza framework consists of the interface layer, core functionality layer, and model layer. The interface layer is responsible for interacting with external platforms, supporting multiple social media platforms and providing API interfaces. The core functionality layer includes the memory system, behavior system, and configuration system. The model layer supports various large language models and provides a unified interface abstraction.
The V2 version will undergo a comprehensive upgrade based on this. First, the interface layer will introduce a unified message bus, integrating the scattered clients into a unified message processing system, simplifying development and maintenance work. The core functionality layer will add a unified proxy wallet, integrating wallet configurations and providing multi-chain wallet management.
In addition, the V2 version will also redesign the core interface to enhance the scalability of the framework and the plugin integration mechanism. The community plugin system will also be improved, achieving 100% test coverage. At the model level, the new version will introduce a model registry mechanism to support dynamic registration and overriding of models, categorizing models into two main types: LLMs and Embeddings, providing a more flexible calling method.
These improvements have made 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 may also bring new development opportunities for related functional expansion plugins.
The continuous evolution of AI Agent technology is pushing the boundaries of intelligent applications. The upgrade of Eliza V2 will undoubtedly provide developers with more powerful and flexible tools for AI Agent development, promising to promote the emergence of more innovative applications. We look forward to this new version bringing positive impacts to the AI Agent ecosystem.