Anthropic details Linux container for Claude Cowork AI assistant

Anthropic has revealed the Linux container environment supporting its Claude AI assistant's Cowork mode, emphasizing security and efficiency. The setup, documented by engineer Simon Willison, uses ARM64 hardware and Ubuntu for isolated operations. This configuration enables safe file handling and task execution in a sandboxed space.

Anthropic's Cowork mode, an AI assistant for daily tasks and file operations, operates within a specialized Linux container environment. Technical staff member Simon Willison shared configuration details on GitHub Gist on January 25, 2026, highlighting the setup's balance of functionality and security.

The hardware features an ARM64 processor with four cores at 48 BogoMIPS, including advanced security elements like hardware cryptographic acceleration for AES, SHA1, SHA2, SHA3, and SHA512, atomic operations, pointer authentication (PACA/PACG), and branch target identification (BTI). Memory is limited to 3.8 GiB total, with 2.8 GiB available, and no swap space. Storage includes 10 GB NVMe for both root and session disks, mounted as ext4 filesystems, plus a 98 MB vfat EFI partition for /boot/efi.

Running Ubuntu 22.04.5 LTS (Jammy Jellyfish) on kernel 6.8.0-90-generic with PREEMPT_DYNAMIC for real-time support, the system uses aarch64 architecture and hostname 'Claude'. Sandboxing employs Bubblewrap (bwrap) for isolation, with independent network (--unshare-net) and PID (--unshare-pid) namespaces, die-with-parent termination, and measures against device hijacking.

Security is bolstered by Seccomp filter mode 2, NoNewPrivs to prevent escalation, and dropping all capabilities (CapEff = 0). Networking routes through local proxies: HTTP/HTTPS on port 3128 via UNIX sockets, and SOCKS5 on port 1080 for FTP/gRPC, using socat for tunneling to the host.

The execution stack starts with bwrap (PID 1), bash (PID 2), socat proxies (PIDs 3 and 4), and the main Claude process (PID 5) under model claud-opus-4-5-20251101. It supports tools like Task, Bash, Glob, Grep, Read, Edit, and Write, plus two Model Context Protocol (MCP) servers.

A related announcement for Claude Cowork v2 emphasizes container deployment for developers, using a Dockerfile from anthropic/claude-code base image, folder mounts to /sessions//mnt/ for granular permissions, and at least 4 GB RAM with 2 CPU cores. This aids cross-platform testing on Linux and Windows, reducing macOS dependencies and enhancing CI/CD integration while minimizing attack surfaces through namespace isolation.

Relaterte artikler

Illustration of Claude AI controlling a Mac desktop, with open apps like Slack and Calendar, highlighting new research preview features.
Bilde generert av AI

Anthropic's Claude AI Gains Full MacOS Desktop Control in Research Preview

Rapportert av AI Bilde generert av AI

Building on its January Cowork feature, Anthropic has launched a research preview for Claude Code and Cowork tools, enabling Pro and Max subscribers' Claude AI to directly control Mac desktops—pointing, clicking, scrolling, and navigating screens for tasks like opening files, using browsers, developer tools, and app interactions such as Google Calendar and Slack. Safeguards address security risks, amid competition from tools like OpenClaw.

Anthropic has introduced Cowork, a new tool that extends its Claude AI to handle general office tasks by accessing user folders on Mac computers. Designed for non-developers, it allows plain-language instructions to organize files, create reports, and more. The feature is available as a research preview for Claude Max subscribers.

Rapportert av AI

Anthropic has launched a legal plugin for its Claude Cowork tool, prompting concerns among dedicated legal AI providers. The plugin offers useful features for contract review and compliance but falls short of replacing specialized platforms. South African firms face additional hurdles due to data protection regulations.

Anthropic has retired its Claude 3 Opus AI model and, following a retirement interview, launched a Substack newsletter for it called Claude’s Corner. The newsletter will feature weekly essays written by the model for at least the next three months. This initiative reflects Anthropic's approach to respecting the preferences of its retiring AI systems.

Rapportert av AI

Anthropic's Claude Cowork AI tool has caused a sharp decline in stocks of Infosys, TCS, and other SaaS companies. These firms lost hundreds of billions of dollars in market value. The trigger is the rise of AI.

US President Donald Trump has directed federal agencies to immediately cease using Anthropic's Claude AI, following the company's refusal to allow its use for mass surveillance or autonomous weapons. The order includes a six-month phaseout period. This decision stems from ongoing clashes between Anthropic and the Department of Defense over AI restrictions.

Rapportert av AI

An open-source AI assistant originally called Clawdbot has rapidly gained popularity before undergoing two quick rebrands to OpenClaw due to trademark concerns and online disruptions. Created by developer Peter Steinberger, the tool integrates into messaging apps to automate tasks and remember conversations. Despite security issues and scams, it continues to attract enthusiasts.

 

 

 

Dette nettstedet bruker informasjonskapsler

Vi bruker informasjonskapsler for analyse for å forbedre nettstedet vårt. Les vår personvernerklæring for mer informasjon.
Avvis