
Author: Ningning
I spent some time studying the current version of Eliza, the AI Agent framework of AI16Z, and the V2 version revealed by Shawn.
Before comparing, let’s first understand the basic architecture of the current version and V2 version.
As shown in Figure 1, the current version of Eliza framework consists of an interface layer, a core functional layer, and a model layer.
Interface Layer
-
Responsible for interaction with external platforms
-
Supports Discord, Twitter, Telegram and other platforms
-
Provide API interface for other system calls
Core Layer
-
Memory system: Provides retrieable storage functions and document processing capabilities
-
Behavior system: manage custom behaviors and action execution
-
Configuring the system: manage configuration via .env and elizaConfig.yaml
Model Layer
-
Supports a variety of large language models, including OpenAI, Anthropic, Llama, Grok, etc.
-
Provides a unified model interface abstraction
The interaction between the layers is through standard interfaces, supporting a high degree of modularity and scalability.
On the 15th, Shawn revealed that the Eliza v2 version is being developed, and the alpha version is expected to be released in 2 to 3 weeks.
Eliza v2 unifies the message bus and simplifies the client; a unified Agent wallet; the model system adopts registry and coverage mode; enhances the scalable common core framework; updates community plug-ins; completes 100% test coverage.
The architecture design diagram of V2 version is as follows:
Let me explain the main improvements of Eliza v2 and their place in the architecture:
Improvements to the interface layer: Unified message bus
-
Change the original decentralized client integration into a unified message processing system
-
Various platforms (Discord/Twitter, etc.) become adapters for message bus
-
Simplified client development and maintenance
-
Provide a more consistent message processing experience
Improvements to the core functional layer: Unified proxy wallet
-
Integrate the original decentralized wallet configuration
-
Provide unified multi-chain wallet management
-
Simplify cross-chain operations
Extensible Core Framework: Redesign the core interface to make it more versatile
-
Enhance the scalability of the framework
-
Better plug-in integration mechanism
Community plug-in update: Improved plug-in system
-
Improve plug-in management
-
100% test coverage guarantees quality
Improvements to the model layer: Introducing the model registry mechanism
-
Supports dynamic registration and override 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, and the interaction between different components is clearer, which also provides a better foundation for future expansion.
Finally, if you analyze it from an investment perspective, Eliza v2 will bring new growth opportunities to feature extension plugins such as AgentTank.