Anthropic opens self-hosted Claude Managed Agents in private beta
Original title: Self-hosted Claude Managed Agents keeps agent credentials in your environment
Customers run the agent server, PostgreSQL session store and workers; Claude model calls still leave the network.
Anthropic opened a private beta of self-hosted Claude Managed Agents on November 12. Customers run the Managed Agents server, a PostgreSQL database for session history, and workers for shell and file tools, so credentials can stay in their own secrets manager. Model calls can go to Anthropic, Amazon Bedrock, Google’s Agent Platform, Microsoft Foundry or a customer gateway, but Claude still executes outside the network. Customers also own host allowlists, OpenTelemetry logs, patching and firewall rules.
- Access is requested through the customer’s Anthropic account team.
- Previously, customers could host only the sandbox, not credential handling.
- A proxy outside the sandbox attaches credentials for MCP and supported API calls.
- Zero data retention agreements cover these calls like other Messages API requests.
- Vendors
- Anthropic
- Products
- Claude Managed Agents
- AI models
- Claude
From the original article
2 min read at helpnetsecurity.com
Anthropic has released a self-hosted version of Claude Managed Agents. Companies can run the agent harness, sandboxes, credentials, and session history in their own cloud or on-premise. The option opened as a private beta on November 12, and customers request access through their Anthropic account team.
By Anamarija Pogorelec · helpnetsecurity.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.