Deep Agent Architecture - Deep agents utilize a planning tool to strategize task execution [4][5] - They employ a file system for organized context and information management, preventing context window overload [5] - Deep agents leverage specialized sub-agents to execute specific tasks, such as research or critique [5][6][18] - A detailed system prompt guides the overall operation of agents and sub-agents [6][10] Implementation and Usage - The process involves cloning the deep agents JS repository and the deep agents UI repository [7][13][14][19] - Configuration requires setting up environment variables, including API keys for web search (Tilli API key) and LLM provider (Anthropic API key), as well as specifying the Langraph server URL and agent ID [8][15][16][19] - The deep agent is instantiated using the `create deep agent` function, which requires a list of tools, instructions, and optionally, sub-agents [9][10] - The Langraph server is initiated using the command `npx langchain langraph cli dev` [8][13] - The deep agents UI runs on localhost 3000, allowing users to interact with the agent [16]

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]