DAGentAn open-source Python library for creating AI agents structured as Directed Acyclic Graphs (DAGs) to manage decision-making tasks and function executions.

DAGent is an open-source Python library for creating AI agents structured as Directed Acyclic Graphs (DAGs) to manage decision-making tasks and function executions. It allows users to create a workflow by setting each function up as a node in a graph, and the agentic behavior is through the inferring of what function to run through the use of Large Language Models (LLMs) abstracted by a 'Decision Node'. The library supports using different LLM models for inference and tool description generation, and tool functionality can be easily added by creating a Python function with a specific signature. The .compile() method autogenerates and saves tool descriptions under a Tool_JSON folder, allowing users to easily customize and manage their AI agents. DAGent provides a straightforward and intuitive API for building AI agents, making it a valuable tool for users looking to leverage the power of LLMs in their applications. In summary, DAGent is a Python library that enables users to build directed acyclic graphs (DAGs) to manage decision-making tasks and function executions using Large Language Models (LLMs). It supports different LLM models and provides a simple API for building AI agents. DAGent has various use cases in areas such as chatbots, automating tasks, and decision-making applications, among others. Its modularity and flexibility make it a suitable choice for users looking to integrate the power of LLMs into their projects. Overall, DAGent is a powerful library for creating AI agents, offering a high degree of customization and flexibility through its modular architecture and support for multiple LLM models. It is worth noting that DAGent is an opinionated Python library, which might make it less suitable for users who prefer a more flexible or generic library.