cd /news/artificial-intelligence/microsoft-is-about-to-let-copilot-lo… · home › topics › artificial-intelligence › article
[ARTICLE · art-147259] src=machinebrief.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Microsoft is about to let Copilot loose on your file system

Microsoft announced hybrid intelligence for Windows that gives Copilot access to files on a user's PC, with local agents running in Execution Containers (MXCs) and a HydraFusion model router deciding between on-device models and cloud models such as OpenAI's GPT-6 or Anthropic's Claude. Microsoft EVP of Windows and Devices Pavan Davuluri said MXCs make Windows "the most secure platform for agents." The functionality rolls out to GitHub Copilot next week and to the Copilot app over the next few months, alongside Windows ML support for Llama.cpp and a new onboarding experience for deploying agent harnesses like OpenClaw.

read3 min views5 publishedOct 7, 2026
Microsoft is about to let Copilot loose on your file system
Image: Machinebrief (auto-discovered)

Source:

The Register But don't worry, it's totally safe because the agents and models will (probably) be running locally. Routers never break right?

If you thought Windows Recall was creepy, buckle up. Microsoft is about to shoehorn even more AI into its desktop operating system, giving Copilotaccess to every file on your PC. But don't worry, Redmond insists it's totally secure and safe since the agents powering the functionality will run entirely on your PC — some of the time. Microsoft describes the new functionality, announced alongside a newNvidiaN1X powered Surface Laptop, as "hybrid intelligence." Built atop Microsoft's HydraFusion model router, Windows apps and Copilot features will soon be able to use local models when it makes sense and cloud-based models when it doesn't. For example, Windows might use a local model for simple or privacy-sensitive tasks, or decide complex or performance-sensitive requests needOpenAI's GPT-6 orAnthropic'sClaude. Local agents will run in Microsoft's Execution Containers (MXCs), agent sandboxes with fine-grained permissions applied at runtime. According to Microsoft EVP of Windows and Devices Pavan Davuluri, MXCs mean Windows is now "the most secure platform for agents." (That claim will surely age well because models never escape their sandboxes and routers never misbehave.) To support this hybrid intelligence functionality, Microsoft is extending support for Windows ML, itsinferenceframework built on the ONNX runtime, toLlama.cpp – one of the highest-performing inference engines for local AI inference. By adding support for Windows ML, Llama.cpp should be able to take advantage of a broader range of accelerators. Microsoft is rolling out its hybrid intelligence functionality to GitHub Copilot — its AI code assistant — next week and its Copilot app over the next few months. The new Copilot features look and sound suspiciously like OpenClaw in a business suit. Copilot's agentic functionality will not have access to your entire file system, opening the door to advanced search functionality and productivity tasks through integrations with Microsoft Office. In a demo, Microsoft showed how Copilot could be used to find and organize a user's tax documents, then draft an email with those files attached, addressed to an accountant. Microsoft insists it'll only go snooping through your docs if you ask it to. Windows is also getting AI-enhanced search functionality enabling users to surface settings like dark mode. The OS will also get a conversational interface to perform tasks like sending a text message to a friend. Finally, for those interested in coloring outside Microsoft's agentic lines, the company is rolling out a new onboarding experience to make deploying agent harnesses like OpenClaw a bit easier and more secure. Keeping sensitive tasks on device may help to assuage anxieties over privacy, which have dogged Microsoft since the first Copilot+ PCs arrived in 2024 alongside Qualcomm's Snapdragon X Elite SoCs. It should also help to reduce the load on Microsoft's servers by keeping low-priority, low-complexity requests on devices. That said, the impact of running these models locally on battery life, fan noise, and workload quality could prove a turnoff for many users. ® Get AI news in your inbox

Daily digest of what matters in AI.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @microsoft 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/microsoft-is-about-t…] indexed:0 read:3min 2026-10-07 · —