Aurora provides a modular architecture for constructing generative AI agents that can autonomously tackle complex tasks through iterative planning and execution. It consists of a Planner component that breaks down high-level objectives into actionable steps, an Executor that invokes these steps using large language models, and a Tool integration layer for connecting APIs, databases, or custom functions. Aurora also includes memory management for context retention and dynamic re-planning capabilities to adjust to new information. With customizable prompts and plug-and-play modules, developers can rapidly prototype AI agents for tasks like content generation, research, customer support, or process automation, while maintaining full control over the agent’s workflows and decision logic.

FreeAct leverages a modular architecture to streamline the creation of AI agents. Developers define high-level objectives and configure the planning module to generate stepwise plans. The reasoning component evaluates plan feasibility, while the execution engine orchestrates API calls, database queries, and external tool interactions. Memory management tracks conversation context and historical data, allowing agents to make informed decisions. An environment registry simplifies the integration of custom tools and services, enabling dynamic adaptation. FreeAct supports multiple LLM backends and can be deployed on local servers or cloud environments. Its open-source nature and extensible design facilitate rapid prototyping of intelligent agents for research and production use cases.