Anthropic launches self-hosted Claude Managed Agents in private beta for on-prem deployment
ClaudeDevs · x · 2026-11-13
Anthropic announced that Self-hosted Claude Managed Agents is now in private beta. Developers can run the full agent stack — harness, sandboxes, credential handling, and session history — inside their own cloud or on-premises environment, and choose where Claude inference requests are routed (Claude Messages API, Amazon Bedrock, Google Agent Platform, or Microsoft Foundry).
It targets unattended agent work that needs access to internal systems, such as fixing broken builds, testing releases, and triaging alerts. Per the architecture diagram, the Managed Agents Server sits inside the customer's network boundary, dispatches tool execution to sandboxes via a work queue, and keeps state in PostgreSQL — only model calls leave the perimeter.
Access is limited to eligible organizations via the Anthropic account team.
Related event: Anthropic Launches Self-hosted Managed Agents in Private Beta(3 posts)→
More from coding & agent
- Open-source flight search MCP server refuses to answer what it can't confirm, curbing model hallucination — Fast_Entrance7839 · 2026-11-13
- Amplitude launches Wave: AI that decides what to build next from product data — testingcatalog · 2026-11-13
- jxnlco: when AI makes you faster, go deep on new things and grow your taste — jxnlco · 2026-11-13
- Vibe-coded space-defense game ORBITAL SIEGE shows Three.js gameplay from one prompt — kimmonismus · 2026-11-13
- AI-generated WebGL2 shader bends light around a black hole on the first try — kimmonismus · 2026-11-13
- Sententos puts a personal agent in your Mac's notch that can take over your screen — ycombinator · 2026-11-13