Deep Agents is a framework for building smart AI assistants. It helps you create agents that can plan tasks, remember past conversations, and use special tools. You can add subagents to handle different jobs. A human can approve important actions. All of this works automatically so you do not have to build everything from scratch.
Developers use Deep Agents when they need to solve complex problems that take many steps. It works with LangChain and LangGraph. The framework comes with built in features like task lists, file management, and long term memory. You just configure what you need and the agent handles the rest.
This skill shows you how to call create_deep_agent() and set up your own agent. It includes example code in Python and TypeScript. You can use it to make agents that work across different sessions and use custom tools.
Global
mkdir -p ~/.claude/skills/deep-agents-coreProject
mkdir -p .claude/skills/deep-agents-coreSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly