> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-remove-1782434199-4494406.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Managed Deep Agents
> Overview of Managed Deep Agents private beta features, workflows, and limits.
Managed Deep Agents is a hosted runtime for deploying and operating Deep Agents in LangSmith. Use it to run durable, long-running agents without standing up your own agent server.
It pairs the [Deep Agents](/oss/python/deepagents/overview) harness with managed infrastructure: durable runs, [LangSmith sandboxes](/langsmith/sandboxes), thread state, MCP tools, file trees, traces, and agent revisions.
Managed Deep Agents is in **private beta**, available on [LangSmith Cloud](/langsmith/cloud) in the US region only. [Join the waitlist](https://www.langchain.com/langsmith-managed-deep-agents-waitlist) to request access.
**Private beta API update:** Managed Deep Agents is moving to a CLI-first private beta surface while we finalize the supported API story. Previous API-driven creation, update, and invocation examples have been removed from these docs. If you built against those preview APIs or need to use agents programmatically, contact your LangChain team; more guidance will be shared during private beta.
The recommended workflow is:
1. Create or edit a local Managed Deep Agents project.
2. Keep the default backend or opt into a LangSmith sandbox backend.
3. Connect MCP tools when the agent needs external capabilities.
4. Deploy the project to Managed Deep Agents.
5. Inspect traces, files, tool calls, runtime state, and revisions in LangSmith.
## Follow the workflow
Deploy a first agent with the CLI.
Register static-header or OAuth MCP servers and reference their tools from agents.
Create or update Managed Deep Agents with the CLI.
Review all deploy commands, project files, flags, and validation rules.
## Use Managed Deep Agents
Use Managed Deep Agents to:
* Create and manage deep agents from local project files.
* Run long-running agents without standing up a custom agent server.
* Give each thread or agent isolated LangSmith sandbox resources for code execution, filesystem work, and long-running tasks.
* Use a managed file tree for instructions, skills, subagents, tools, and runtime files.
* Register workspace-level MCP servers, including OAuth MCP servers, and list their available tools.
* Inspect traces and agent behavior in LangSmith.
You can also deploy Deep Agents with a standard [LangSmith Deployment](/langsmith/deployment-quickstart). Use that path when you need custom application code, custom routes, advanced authentication, full Agent Server APIs, stronger isolation controls, or maximum scalability.
## Created resources
When you create a Managed Deep Agent, LangSmith provisions:
* A Managed Deep Agent resource.
* A separate [LangSmith tracing project](/langsmith/observability-concepts#projects) for the agent.
* A [Context Hub](/langsmith/use-the-context-hub) agent repo that stores the managed file tree.
It does not create a LangSmith Deployment.
Managed Deep Agent runs are traced in the separate tracing project created for the agent. Open traces in LangSmith to inspect user inputs, final responses, model calls, tool calls, subagent activity, files, and runtime state created during the run.
The Context Hub agent repo stores the managed file tree for the agent, including instructions, skills, subagents, and tool configuration.
## LangSmith sandbox backends
Managed Deep Agents projects generated by `deepagents-cli>=0.2.2` use the `state` backend:
```json theme={null}
{
"backend": {
"type": "state"
}
}
```
LangSmith sandboxes are isolated environments for operations such as running code and interacting with a filesystem without affecting your main infrastructure. In Managed Deep Agents, they give agents a managed runtime for long-running work while LangSmith handles the underlying sandbox lifecycle.
Choose the backend that matches your scope:
* `state`: applies no sandbox-specific backend behavior.
* `sandbox` with `sandbox_config.scope: "thread"`: scopes sandbox resources to each thread.
* `sandbox` with `sandbox_config.scope: "agent"`: scopes the sandbox to the agent rather than to individual threads.
For standalone sandbox concepts, see the [LangSmith sandboxes overview](/langsmith/sandboxes). For Managed Deep Agents configuration fields and validation rules, see [Deploy an agent](/langsmith/managed-deep-agents-deploy#choose-a-backend) and the [CLI reference](/langsmith/managed-deep-agents-cli#project-file-reference).
## Limits and notes
Operational notes that apply during private beta. Behavior may change before general availability.
### Stable deploy experience
Managed Deep Agents deploy is available through the beta CLI release during private beta. The stable Deep Agents deploy experience continues to work until Managed Deep Agents reaches public beta and the deploy command switches to the new behavior.
### Supported models
Pass model identifiers in the form `{provider}:{model_id}`. For example, `openai:gpt-5.5`. The runtime resolves models with `init_chat_model`, so any provider that `init_chat_model` supports is usable from Managed Deep Agents. See [Supported providers and models](/oss/python/langchain/models#supported-providers-and-models) for the current list.
Values without a colon are interpreted as references to a saved Playground configuration rather than as model identifiers. Always supply the full `{provider}:{model_id}` form when configuring a model directly.
### Thread retention
Threads have no retention window or per-workspace cap during private beta. Create as many as you need. Existing threads remain accessible for the duration of the beta.
### Rate limits and quotas
The Managed Deep Agents endpoints do not enforce per-key, per-workspace, or per-agent request rate limits during private beta.
### Agent limits
Free LangSmith workspaces are limited to one Managed Deep Agent. Paid LangSmith plans can create unlimited agents. When a free workspace is already at its limit, `deepagents deploy` fails with a message to delete the existing agent or upgrade your plan.
### Delete agents
Deleting an agent does not cascade to threads. Threads created against a deleted agent remain queryable but cannot start new runs. Track and delete threads explicitly when you want to clean them up.
### API stability
Managed Deep Agents is repo- and CLI-first during private beta. The agent-creation APIs are not part of the documented product surface. Use the CLI for creation, updates, MCP server registration, and deploy workflows.
### Support and feedback
Beta access includes direct support. The contact for bug reports and feature requests is included in the email you receive when access is granted.
## Private beta scope
Managed Deep Agents is available on LangSmith Cloud in the US region only during private beta. Self-hosted and Hybrid deployments are not supported, and EU and other regions are planned after general availability.
The API also does not mirror every LangSmith Deployment endpoint in private beta. A Managed Deep Agent is not a LangSmith Deployment.
***
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/managed-deep-agents-overview.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).