BriefsToolBeta
LangChain launches Managed Deep Agents in public beta for AI deployment
Developers can now build deep AI agents as a folder of files and deploy them directly to LangSmith Cloud.
Summary
LangChain introduced Managed Deep Agents in public beta on LangSmith Cloud. The system lets developers define a deep agent as a folder of files and ship it with one command. It handles server operations, durable threads, and streaming runs automatically.
What changed
- LangChain released Managed Deep Agents in public beta on LangSmith Cloud.
- Developers define agents as a folder of files with a required agent.py file.
- The CLI command mda dev starts a local Agent Server for testing in LangSmith Studio.
- The CLI command mda deploy ships the project to LangSmith with the model provider key.
- Adding memory.py keeps knowledge across threads for users and callers.
Availability
Beta“Managed Deep Agents is in public beta on LangSmith Cloud, and this post now describes how it works today.”
Founder takeaway
Developers building production AI agents can test the Managed Deep Agents public beta on LangSmith Cloud to deploy agents from project folders without managing infrastructure.
Source
Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.
Related
More briefs
Nvidia releases Workload Map to standardize AI workload parsing on Kubernetes
Nvidia introduces Workload Map, an open-source tool providing prebuilt definitions to interpret distributed AI frameworks without custom parsers.
NVIDIA1 min read
AWS updates the Amazon Textract AI text detection model
AWS released an updated text detection model for Amazon Textract that expands language support to over 40 languages and improves multilingual table extraction.
AWS1 min read
Vercel MCP now supports client ID metadata documents
Vercel MCP added support for client ID metadata documents, allowing any model context protocol client to connect without prior manual review.
Vercel1 min read
One email, every Monday
Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.
One email. Every Monday.