Introduction

OpenAgent is an open-source framework for building AI applications leveraging the power of blockchains and RSS3 Network.

The framework drastically shortens the development time of AI Agents from months to hours.

OpenAgent defines an AI Agent with five conceptual components:

Client: a user interface for interactions
(App Server): a server to store user-related data like user info, chat history, etc. (Optional)
Interpreter: an LLM (or multiple LLMs) to invoke the appropriate expert based on messages received
Experts: a group of experts that are designed to complete subtasks Information Source: a source that experts depend upon to determine the next step. This is the Mixture-of-Experts (MoE) technique that divides complex tasks into simpler sub-tasks.
Executor: a special type of expert to execute transactions on chain

Customizability

Adding new Experts is easy and offers unlimited possibilities to your AI Agent.

Add your Expert under backend/openagent/experts with the logic to interact with external data sources and corresponding prompts. The directory contains some example Experts to get you started.
Add the Expert in backend/openagent/agent/function_agent.py to enable it, and you are done.