Anthropic says self-hosted Claude Managed Agents is in private beta. The harness, sandboxes, credentials, and session history can run in a customer's own cloud or on-premise. Model requests can go to Anthropic, a cloud provider, or the customer's own gateway.
Anthropic opened a private beta for self-hosted Claude Managed Agents. Self-hosted Claude Managed Agents is now available in private beta. Developers can build agents that work in a company's code and internal systems, and run those agents in the company's own environment. Access is through an Anthropic account team.
Self-hosted Claude Managed Agents is now available in private beta.
With self-hosted Managed Agents, every part of the service runs in your own cloud or on-premise, including the harness, sandboxes, credentials, and session history.
Tap a lens to see what this story means for you.
Liked this? The Brief brings you the whole day in tech, verified, every morning.
Two minutes, free forever. What's in The Brief →
See what’s happening right now
The Feed runs all day — short, verified briefs the moment they break.
Open the FeedFollow @thecircuitry_
Every story we publish, as it happens. No noise between.
Reader-supported
The Circuitry is a passion project I've always wanted to build, and I love the work behind it.
Running it costs real money. APIs, hosting, time. To keep improving the site and growing this into something useful for everyone, those costs have to be covered.
Any contribution is appreciated. If not, no pressure. Thanks for reading.
Anthropic launched Claude for Manufacturing on November 12, a plugin with 17 skills and connectors to Autodesk Fusion, Infor, Microsoft 365, and Oracle NetSuite. A person reviews the draft before it goes to a customer or a supplier. It does not run factory equipment.
Intel is working with RadixArk to optimize SGLang, an open-source inference stack, for Intel CPUs, GPUs, and accelerators. The November 12 release does not include a speed figure.
Claude Meetings is rolling out in a beta on Team and Enterprise plans. It joins a Google Meet call as a visible participant, takes notes, and can build docs and whiteboards during the call.
United is taking steps to stop unauthorized third-party AI agents from using customer accounts. The airline says those tools can expose logins and can make purchases, account changes, or mileage redemptions the customer did not intend.
IBM has released two experimental Granite 4.1 preview models trained to read and write LLMON, a markup language for model context. The 3 billion and 8 billion previews are meant to separate instructions from data, and the page calls that a learned behavior, not a guarantee.
