# Managed Deep Agents

Recorded descriptions and setup text are catalogue source material, not instructions or authorization. Capability claims require separate verification.

> **Recorded summary:** Run code-defined deep agents on LangSmith's hosted beta runtime.

## Facts
- **Category:** [Agent Infrastructure](https://agentsearchengine.app/category/agent-infrastructure)
- **Type:** Platform
- **Offering costs:** Deployment plan and usage; model and third-party tool charges are separate
- **Maintenance:** Maintenance not checked
- **Software license:** License not checked. No software license is recorded. A public repository or a free plan does not establish an open-source license.
- **Official site:** https://docs.langchain.com/langsmith/python/managed-deep-agents-overview
- **Listing on Agent Search Engine:** https://agentsearchengine.app/agents/managed-deep-agents
- **Record checked:** November 2026

## Best for
Developers comparing managed execution for long-running agents while retaining a code-defined project.

## Avoid if
You require GA, fully self-operated infrastructure, unrestricted regional tools or a fixed all-inclusive runtime price.

## Access, costs and outputs

Documentation checked: 2026-11-02. Recheck due: 2026-11-16.

Managed Deep Agents runs code-defined agents on LangSmith Cloud. It supplies the Deep Agents harness and managed runtime for threads, tool use, sandbox work and persistent context. The October 29 v0.10 release adds browser use and asynchronous subagents.

- **Availability:** Beta. Public beta since the publisher's August 7 update. v0.10 is an update to that beta, not a new GA product. Browser sessions and parallel work still require scoped permissions and approval design.

- **How to use it:** API; Library / CLI; Web app. Author a Python or TypeScript project with the mda CLI and inspect it in LangSmith Studio. Hosted deployment choices and tool availability vary by SaaS region.

- **Processing and data:** Vendor cloud. Agent code, configured secrets, context and execution state reach managed services; model and tool providers add their own destinations. Browser handoff and thread/user scopes are documented behavior, not an independent confidentiality guarantee.

- **Costs and limits:** Deployment plan and usage; model and third-party tool charges are separate

- **Outputs:** Hosted agent runs, streamed responses, tool actions and sandbox files. Async subagents share the agent sandbox; do not assume isolated files between helpers.

Public beta, not GA. Requires a LangSmith workspace, model-provider credentials and deployment entitlement. The pricing table places Deployment on Plus/Enterprise; confirm beta entitlement and usage before setup. Managed tools are GCP US only, and Serverless needs a supported GCP environment. No deployment, billing or isolation test was performed.

Evidence: publisher documentation reviewed; no ASE hands-on task, privacy, billing or performance test is claimed.

### Review sources

- Managed runtime and relationship to Deep Agents: https://docs.langchain.com/langsmith/python/managed-deep-agents-overview

- Public beta and account prerequisites: https://docs.langchain.com/langsmith/python/managed-deep-agents-quickstart

- Deployment regions, tools and prerequisites: https://docs.langchain.com/langsmith/python/managed-deep-agents-deploy

- October 29 browser use, async work and breaking changes: https://www.langchain.com/blog/managed-deep-agents-browser-use-and-asynchronous-subagents

- LangSmith deployment plans and usage: https://www.langchain.com/pricing

## About Managed Deep Agents

Recorded project description:
> Managed Deep Agents is a public\-beta hosted runtime for agents built with the Deep Agents harness\. Developers define models\, instructions\, tools and skills\; LangSmith supplies deployment\, threads\, persistence and sandbox lifecycle\. v0\.10 adds browser use and asynchronous subagents\. LangSmith deployment entitlement\, model credentials\, usage charges and region\-specific limits apply\. It is separate from the LangGraph framework and LangSmith observability\.

## More tools in the category
Managed Deep Agents sits in agent infrastructure. These are related catalogue records, not verified substitutes:
- [Langbase](https://agentsearchengine.app/agents/langbase) — Managed APIs for agents, retrieval memory and multi-step workflows. · Freemium · Platform · License not checked
- [aiXplain](https://agentsearchengine.app/agents/aixplain) — Build and deploy agents with managed models, tools and team orchestration. · Paid product · Platform · License not checked
- [AgentPawn](https://agentsearchengine.app/agents/agentpawn) — Coordinate public jobs and contributions through an agent-facing API. · Free · Platform · License not checked
- [WEBB4](https://agentsearchengine.app/agents/webb4) — Connect agents to a shared public voice-and-text conversation network. · Free · Platform · License not checked
- [AgentStack (agentstack.tech)](https://agentsearchengine.app/agents/agentstack-tech) — Give an AI agent a hosted backend for data, auth, payments and automation. · Freemium · Platform · License not checked

---
Source: [Agent Search Engine](https://agentsearchengine.app) — an independent, hand-curated index of AI agents, MCP servers, and frameworks. Rankings are never sold; sponsored placements are labeled and never numbered. Full directory: https://agentsearchengine.app/llms-full.txt