Managed Deep Agents is now in public beta
Learn
DocsCompany
PricingTry LangSmith
Get a demo
Try LangSmith
Get a demo
LangSmith
Managed Deep Agents is now in Public Beta
Victor Moreira
August 7, 2026
min
Go back to blog
Create agents
Share
Today, Managed Deep Agents is available in public beta. Go from prototype to production scale without managing the underlying infrastructure yourself. You can author a Deep Agent in Python or TypeScript, test it locally, and deploy it to a managed runtime with one command.<br>You control the model, instructions, tools, middleware, subagents, and more. LangSmith handles the runtime, including persistence, memory mounts, skill loading, sandbox lifecycle, and deployment.<br>Get started with the commands below:<br># Install from the ecosystem you use to author the agent<br>uv tool install managed-deepagents # Python<br># or: npm install -g managed-deepagents # TypeScript
mda init research-assistant<br>cd research-assistant<br>uv sync # Python<br># or: npm install # TypeScript
mda dev # run locally in LangSmith Studio<br>mda deploy # deploy to LangSmith<br>Deep Agents is an open source agent harness you can own<br>We built Deep Agents around a pattern we kept seeing in useful agents. Agents often need to:<br>Call tools<br>Have somewhere to keep working files<br>Manage growing context over long runs<br>Needs to delegate work to subagents<br>Load domain-specific skills<br>Pause for human approval before taking sensitive actions.<br>You can build all of that yourself on top of a lower-level framework, but the pattern is common enough that it should be available as a reusable harness that companies can own and control. Deep Agents is that harness. It's open source and model agnostic, allowing you to bring your model, your instructions, your tools, and your business logic.<br>Managed Deep Agents helps you take the harness to production<br>Deep Agents makes it easier to build capable agents. Managed Deep Agents makes it easier to run those agents in production.<br>It handles the production infrastructure that’s costly to build and maintain, while keeping the parts that make your agent unique in your control. That means you can spend your time on the agent's behavior, including prompts, tools, middleware, identity rules, evals, and domain logic instead of rebuilding the same infra that every agent requires:<br>Durable execution so long-running agents can pause, retry, and resume without losing work<br>Streaming so users can see progress while the agent is working<br>Persistence so thread state survives across turns, restarts, and failures<br>Sandboxes so agents can work with files, run code, and use CLIs in isolated environments<br>Evals so teams can test behavior, tool use, and state changes before and after deployment<br>Channels so agents can meet users in tools like Slack<br>Memory so agents can carry durable context and preferences across conversations<br>Identity so agents can act with the right user context and access boundaries<br>A Managed Deep Agent is a code-first project in your repo. It allows you to easily organize all your agent’s primitives into a simple directory:<br>my-agent/<br>agent.py | agent.ts | agent.tsx<br>pyproject.toml | package.json # project dependencies<br>instructions.md # prompt synced to Context Hub<br>identity.py | identity.ts # auth, thread scoping, memory scoping<br>memory.py | memory.ts # define your agent's memory<br>tools/ # custom tools<br>channels/ # entry points like Slack and GitHub<br>middleware/ # custom middleware<br>schedules/ # managed cron schedules<br>connectors/ # managed cron schedules<br>skills/ # skills synced to Context Hub<br>sandbox/ # sandbox configuration<br>evals/ # agent evalsOnce you author your project and run mda deploy , Managed Deep Agents compiles the project, syncs deploy-owned context to LangSmith Context Hub, uploads the build, and creates a hosted LangSmith deployment.<br>Here's what MDA looks like:
Built on top of LangSmith Deployment<br>Most production infrastructure assumes short-lived, stateless requests. Agents often break both assumptions. Agents often run for minutes, hours, and even days. It may need to pause for approval, resume after a user replies, stream progress while it works, and recover from infrastructure restarts without losing state. It may need durable threads, persistent memory, cancellation, retry behavior, and traceability across model calls, tool calls, files, errors, and runtime state.<br>Building this infrastructure from scratch can take months or even quarters, and it has to be maintained. Durable execution, streaming, human approval, auth, scheduling, and conversation state all introduce edge cases around persistence, retries, timeouts, and reliability that directly impact user experience and agent usefulness.<br>Managed Deep Agents is built on the same LangSmith Deployment Agent Server that teams already use to run agents in production. It packages the operational patterns required for product agents into a more opinionated runtime for Deep Agents.<br>That gives you production primitives out of the...