Managed Deep Agents
langchain-ai/langchain-skillsManaged Deep Agents let you create and run smart AI agents right inside LangSmith. You do not need to manage servers or worry about infrastructure. The runtime handles threads, streams, and file storage for you.
Use the command line, Python, or TypeScript to build and deploy your agent. You can also add MCP servers for extra tools. A simple chat interface built with React can stream results live.
This skill covers everything from setting up a project to running a durable thread. It helps you choose between the hosted version and a self-hosted setup. Perfect for anyone who wants to focus on building agents without operational overhead.
Add Managed Deep Agents skill to your workflow
Global
mkdir -p ~/.claude/skills/managed-deep-agentsProject
mkdir -p .claude/skills/managed-deep-agentsSource Repository
More AI & Agent Building Claude Code Skills
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