Managed Deep Agents quickstart

Create and deploy your first Managed Deep Agent with the CLI.

LangChain hosts Managed Deep Agents, so you can deploy a Deep Agent without setting up infrastructure. This quickstart shows how to scaffold a local project, edit the agent instructions, and deploy it with the CLI.

For the full deploy workflow and all backend options, see Deploy an agent.

Managed Deep Agents is in private beta, available on LangSmith Cloud in the US region only. Join the waitlist to request access.

Prerequisites

Before you start, make sure you have:

• Managed Deep Agents private beta access.
• A LangSmith API key for a workspace with private beta access.
• The deepagents-cli>=0.2.2 package.

Create and deploy an agent

1. Install the CLI

   Install deepagents-cli with uv (preferred) or pip:

   uv

   uv tool install "deepagents-cli>=0.2.2"
   

   pip install -U "deepagents-cli>=0.2.2"
   

   To upgrade an existing CLI installation, run uv tool upgrade deepagents-cli (or pip install -U "deepagents-cli" if you installed with pip).

2. Set your API key

   Set a LangSmith API key for a workspace with private beta access:

   export LANGSMITH_API_KEY="<LANGSMITH_API_KEY>"
   

   If a request returns 401 or 403, confirm your API key belongs to a workspace with private beta access.

3. Create a project

   Create a Managed Deep Agents project:

   deepagents init research-assistant
   cd research-assistant
   

   The CLI creates:

   File or directory	Purpose
   agent.json	Agent metadata, model, backend, and optional target agent_id.
   AGENTS.md	Main agent instructions.
   tools.json	Empty MCP tool configuration.
   skills/example-skill/	Example skill you can edit or remove.
   subagents/researcher/	Example subagent you can edit or remove.
   .gitignore	Excludes local environment files.

4. Edit the instructions

   Open AGENTS.md and replace the generated instructions with the behavior you want:

   AGENTS.md

   # Research assistant
   
   You are a careful research assistant. Search for sources, keep notes, and return
   concise answers with citations.
   

   The generated project uses the state backend so the agent can deploy without sandbox-specific configuration. Switch to the sandbox backend when the agent needs a LangSmith sandbox for code execution, filesystem work, or long-running tasks. For options, see Choose a backend.

   If the agent calls MCP tools, connect tools before deploying the agent.

5. Deploy the agent

   Deploy the local project:

   deepagents deploy
   

   On success, the CLI prints the agent name, ID, short revision, agent URL, and a post-deploy MCP health check:

   Deployed: research-assistant
     agent_id: e2de7a35-9dda-462b-b982-9e57051993bc
     revision: 13ac11f1
     https://smith.langchain.com/o/-/agents/e2de7a35-9dda-462b-b982-9e57051993bc
     health:   {'agent_id': '...', 'mcp_check': {'ok': True, 'servers': []}, ...}
   

   Open the printed agent URL in LangSmith to inspect the deployed agent, managed files, revisions, traces, and runtime behavior.

Next steps

Connect tools

Register MCP servers and reference their tools from tools.json.

Deploy an agent

Review the complete CLI deploy workflow and project file layout.

CLI reference

Review all deploy commands, flags, and validation rules.

LangSmith sandboxes

Learn how sandboxes provide isolated execution environments.

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.