Claude by Anthropic
A family of foundational AI models
5.0•701 reviews•45K followers
A family of foundational AI models
5.0•701 reviews•45K followers
We're an AI research company that builds reliable, interpretable, and steerable AI systems. Our first product is Claude, an AI assistant for tasks at any scale.
This is the 34th launch from Claude by Anthropic. View more
Computer Use in Claude Code
Launching today
Enable computer use in the Claude Code CLI so Claude can open apps, click, type, and see your screen on macOS. Test native apps, debug visual issues, and automate GUI-only tools without leaving your terminal.
Payment Required
Launch Team
ChatGPT by OpenAI
Gemini
Flowtica Scribe
Hi everyone!
Claude can write the code, run it, open the app, click through the interface, and check what actually happened, all from the CLI.
You can enable computer-use from /mcp, grant macOS Accessibility and Screen Recording, approve apps per session, and stop everything instantly with Esc at any time.
Research preview for macOS on Pro and Max plans for now.
This is a game-changer for developer workflows. We use Claude Code heavily for building our PropTech platform and the biggest friction has always been switching between the CLI and GUI tools for testing. Being able to have Claude debug visual issues and automate GUI-only tools directly from the terminal is going to save so much context-switching time. Question — does the screen observation work well with map-heavy interfaces? A lot of our work involves geospatial UIs (Mapbox, zoning overlays) and I'm curious how well it handles those kinds of visually complex layouts.
The GUI-only tools use case is what gets me. So much internal tooling in companies never gets API access - it lives in dashboards, legacy web apps, Figma. This bridges that last mile without needing to build integrations first. Curious how it handles multi-step flows where intermediate state matters - like filling a form where field 2 options depend on field 1.