Skip to main content
mda dev compiles a Managed Deep Agents project and runs it on a local Agent Server. It opens LangSmith Studio so you can interact with the agent and inspect its behavior before deploying.
Managed Deep Agents is in public beta and available on LangSmith Cloud in the US region only.

​
Start local Studio

Install the project dependencies and add the model provider credentials to .env. Python projects also require uv. From the project root, run:
The CLI prints the local server and Studio URLs and opens Studio in your browser. Send messages in Studio to inspect model responses, tool calls, state, and interrupts. After changing project files, stop and rerun mda dev to recompile the project.

​
What mda dev does

mda dev:
  1. Validates the project and compiles it into .mda/build.
  2. Copies the project .env into the local build and adds local-only identity configuration when needed.
  3. Creates a local Context Hub mock for instructions, skills, and memory.
  4. Starts the language-specific LangGraph development server.
  5. Opens the agent in Studio.
Local development does not create or update a hosted deployment.

​
Configure the local server

For all command details, see the mda dev CLI reference.

​
Understand local behavior

mda dev uses local defaults to make testing easier:
  • If the agent uses identity, Studio provides a local test user automatically.
  • If the configured sandbox is unavailable, the agent uses a temporary local folder instead. The CLI prints the folder path.
These defaults differ from a deployed agent. Test identity and sandbox behavior in a development deployment before using the agent in production.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.
Edit this page on GitHub or file an issue.