Anthropic moves Claude Cowork's VM and inference fully into the cloud
Anthropic's Felix Rieseberg described an architecture change for Claude Cowork: the old version ran model inference in the cloud but executed tool calls in an Anthropic-provided VM shipped to the user's computer, added for capability, safety and security reasons and mapping in only the data explicitly added to a session. The new version runs both inference and the VM in the cloud, with each session getting its own sandbox that shares no state with others; when the VM needs something on the user's device, such as a file, the desktop app handles that file-access tool call. Rieseberg said this addresses complaints about the local VM's disk, battery and performance cost, and about work stopping when a laptop is closed.
Why it matters: It shows agent vendors trading local execution for cloud sandboxes so long-running work can continue across devices.
5th October 2026
The "old" version of Cowork runs model inference in the cloud, executing tool calls in an Anthropic-provided VM we shipped to your computer. We added the VM for capability, safety, and security reasons - mapping in just the data you explicitly added to your session. People loved what they were able to do with Claude but didn't love the disk, battery, and performance cost of running the VM locally. Also, people didn't love that closing your laptop means the work stops.
The "new" version of Cowork runs model inference and the VM in the cloud. Each session gets its own sandbox, not sharing state with other sessions. When the VM needs something on the users' device (like a file), the desktop app is responsible for that file access tool call. [...]
We think this solves a lot of problems we've heard about (like using Cowork from a phone, keeping work running, or getting all the same power without losing battery to the VM)
— Felix Rieseberg, Anthropic, see also this help page
How we got here
- OpenAI Faces Expanding Regulatory ScrutinyThe Information · Anthropic
- Anthropic expands Cyber Verification Program to three access tiers for security teamsAnthropic · News · Anthropic
- SemiAnalysis: Anthropic subscriptions offer ~5x OpenAI's API-equivalent valueSemiAnalysis · Anthropic
- Claude Code on Amazon Bedrock comes to AWS GovCloud for regulated workAWS Machine Learning Blog · Anthropic
- Agent swarms may be AI's next scaling law, but gains look limitedUnderstanding AI · Anthropic
- Pentagon says it has stopped using Anthropic AI toolsBBC Technology · Anthropic