The AI Agent framework Eliza V2 version is about to be released, bringing multiple major upgrades.

Recently, AI16Z's AI Agent framework Eliza is about to release version V2, expected to launch the alpha test version in 2-3 weeks. The new version has significant improvements in architecture design and functionality, aimed at enhancing the framework's scalability, unification, and usability.

The current version of Eliza 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, which are respectively responsible for storage retrieval, action execution, and configuration management. The model layer supports various large language models and provides a unified interface abstraction.

The V2 version has undergone several important upgrades based on this foundation:

1. The interface layer introduces a unified message bus, transforming the originally decentralized client integration into a unified message processing system. Each platform acts as an adapter for the message bus, simplifying development and maintenance work, and providing a more consistent message processing experience.

2. The core functional layer has added a unified proxy wallet, integrating the original decentralized wallet configurations, providing unified multi-chain wallet management, and simplifying cross-chain operations.

3. The extensible core framework has been redesigned, the core interfaces are more universal, enhancing the framework's scalability and plugin integration mechanism.

4. The community plugin system has been updated, improving plugin management and ensuring quality through 100% test coverage.

5. The model layer introduces a model registry mechanism that supports dynamic registration and overriding of models, categorizing models into two main types: LLMs and Embeddings, providing a more flexible way to invoke models.

These improvements have made the architecture of Eliza V2 more modular and unified, with clearer interactions between components, laying a solid foundation for future functional expansions. From an application perspective, the new version will bring new development opportunities for functional extension plugins such as AgentTank.

With the release of version V2, the Eliza framework is expected to play a greater role in the AI Agent field, providing developers with more powerful and flexible tool support. We look forward to seeing the official release of the alpha version in the coming weeks, as well as more innovative applications based on the new framework.