Deep Agents Overview - Deep agents are agents that plan, reason, and act over longer time horizons [1][2] - Deep agents can plan their work, delegate tasks to sub-agents, use a file system, and have detailed system prompts [3] - Setting up a deep agent involves cloning a repository, installing dependencies, and specifying API keys [4] UI Setup and Functionality - The UI displays the agent's plan, file system status, and sub-agents [1] - Setting up the UI requires cloning the UI repository and configuring variables like the deployment URL and agent ID [5][6] - The UI workspace pane is connected to the agent's to-do list and file system [7] - The agent writes the user's question to its file system for later reference [7] - Sub-agents can be spawned to handle complex tasks, and their inputs and outputs can be viewed [8] - A critique agent can critique the final report, and the agent can edit specific lines in the file system [9] Key Steps for Implementation - Fork the open-source repository and set environment variables to point to the agent server [10]