Author: Ningning
I spent some time studying the differences between the current version of AI16Z's AI Agent framework Eliza and the V2 version revealed by Shawn.
Before the comparison, let's first understand the basic architecture of the current version and V2 version.
As shown in Figure 1, the current version of the Eliza framework consists of the interface layer, the core function layer, and the model layer.
Interface Layer
Responsible for interaction with external platforms
Support multiple platforms such as Discord, Twitter, Telegram, etc.
Provide API interface for other systems to call
Core Function Layer
Memory system: provides retrievable storage functions and document processing capabilities
Behavior system: manages custom behaviors and action execution
Configuration system: through .env and elizaConfig.yaml Management configuration
Model Layer
Supports a variety of large language models, including OpenAI, Anthropic, Llama, Grok, etc.
Provides a unified model interface abstraction
Each layer interacts through a standard interface, supporting a high degree of modularity and scalability.
On the 15th, Shawn revealed that Eliza v2 is being developed and the alpha version is expected to be released in 2 to 3 weeks.
Eliza v2 will unify the message bus and simplify the client; unified Agent wallet; the model system adopts the registry and coverage mode; enhance the extensible common core framework; update the community plug-in; complete 100% test coverage.
The architecture design diagram of the V2 version is speculated as follows:
Let me explain the main improvements of Eliza v2 and its position in the architecture:
Improvements in the interface layer: unified message bus
Change the original scattered client integration to a unified message processing system
Various platforms (Discord/Twitter, etc.) become adapters of the message bus
Simplified client development and maintenance work
Provide a more consistent message processing experience
Improvements in the core function layer: unified proxy wallet
Integrated the original scattered wallet configuration
Provide unified multi-chain wallet management
Simplified cross-chain operations
Extensible core framework: redesign the core interface to make it more universal
Community plug-in update: Improve the plug-in system
Improvements at the model layer: Introduce a model registry mechanism
Support dynamic registration and overwriting of models
Divide models into two categories: LLMs and Embeddings
More flexible model calling methods
The architecture of this new version is more modular and unified, the interaction between different components is clearer, and it also provides a better foundation for future expansion.
Finally, if analyzed from an investment perspective, Eliza v2 will bring new growth opportunities for functional extension plug-ins such as AgentTank.