LangChain has published managed-deepagents 0.9.0 on PyPI. The package provides the Python authoring interface and the mda CLI for compiling and deploying a code-first Deep Agent repository to a managed LangGraph runtime.
The package documents define_schedule, a Python contract for managed cron schedules. It requires Python 3.9 or later. Each platform wheel includes a prebuilt mda binary for its operating system and CPU architecture, exposed through the mda console script.
An agent can now be exported as a synchronous or asynchronous factory. The factory may select the model, tools, middleware, instructions, skills, MCP definitions, sandbox, and memory for an individual run from its runtime context. The documentation says factories should be repeatable and retain graph structure and schemas.
The PyPI page does not establish pricing, service availability, performance, or a release date. It also does not establish how scheduled agents behave in production beyond the documented authoring contract.