Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discovery
This addresses the problem of fragmented agent development for researchers and developers, offering a unified framework, though it is incremental as it builds on existing agent paradigms.
The paper tackles the lack of standardized tools for LLM-based agents by introducing Cerebrum, an SDK platform that provides a modular architecture for development, a community hub for sharing, and a web interface for testing, demonstrated through implementations like Chain of Thought and ReAct agents.
Autonomous LLM-based agents have emerged as a powerful paradigm for complex task execution, yet the field lacks standardized tools for development, deployment, distribution and discovery of agents. We present Cerebrum, an Agent SDK for AIOS that addresses this gap through three key components: (1) a comprehensive SDK featuring a modular four-layer architecture for agent development, encompassing LLM, memory, storage, and tool management; (2) a community-driven Agent Hub for sharing and discovering agents, complete with version control and dependency management; (3) an interactive web interface for testing and evaluating agents. The platform's effectiveness is demonstrated through implementations of various agent architectures, including Chain of Thought (CoT), ReAct, and tool-use agents. Cerebrum advances the field by providing a unified framework that standardizes agent development while maintaining flexibility for researchers and developers to innovate and distribute their agents. The live website is at https://app.aios.foundation, the code is at https://github.com/agiresearch/Cerebrum, and video is at https://app.aios.foundation/video-demo.