$git clone https://github.com/AmrDab/clawdcursor<!-- ─────────────────────────────────────────────────────────────────────────── DEMO: the single highest-leverage thing on this page for a *visual* tool. Record a 15–25s screen capture of clawdcursor driving a real app end-to-end (open app → find a field by name → type → v
| 1 | <h1 align="center">Clawd Cursor</h1> |
| 2 | |
| 3 | <p align="center"> |
| 4 | <strong>Safe desktop control for any AI agent.</strong> Compiles the screen into a UI map and acts on elements by stable id (screenshot/vision only as a last resort),<br> |
| 5 | <strong>verifies its own actions</strong>, and gates everything through one safety checkpoint. Local · cross-OS · any model. |
| 6 | </p> |
| 7 | |
| 8 | <p align="center"> |
| 9 | <a href="LICENSE"><img src="https://img.shields.io/github/license/AmrDab/clawdcursor?color=a855f7" alt="MIT license"></a> |
| 10 | <a href="https://github.com/AmrDab/clawdcursor/releases/latest"><img src="https://img.shields.io/github/v/release/AmrDab/clawdcursor?color=22c55e&label=release" alt="Latest release"></a> |
| 11 | <a href="https://www.npmjs.com/package/clawdcursor"><img src="https://img.shields.io/npm/v/clawdcursor?color=cb3837&logo=npm" alt="npm"></a> |
| 12 | <img src="https://img.shields.io/badge/node-%E2%89%A520-339933?logo=nodedotjs&logoColor=white" alt="Node 20+"> |
| 13 | <img src="https://img.shields.io/badge/platform-win%20%7C%20mac%20%7C%20linux-0ea5e9" alt="Cross-platform"> |
| 14 | <a href="https://github.com/AmrDab/clawdcursor/actions/workflows/cross-platform.yml"><img src="https://img.shields.io/github/actions/workflow/status/AmrDab/clawdcursor/cross-platform.yml?branch=main&label=tests" alt="Tests"></a> |
| 15 | <a href="https://discord.gg/hW29nrEZ8G"><img src="https://img.shields.io/badge/Discord-join-5865F2?logo=discord&logoColor=white" alt="Discord"></a> |
| 16 | </p> |
| 17 | |
| 18 | <p align="center"> |
| 19 | <a href="#install">Quickstart</a> · |
| 20 | <a href="#why-its-different">Why it's different</a> · |
| 21 | <a href="#the-engine">The engine</a> · |
| 22 | <a href="#how-it-works">How it works</a> · |
| 23 | <a href="#the-toolbox">Tools</a> · |
| 24 | <a href="#platform-support">Platforms</a> · |
| 25 | <a href="CHANGELOG.md">Changelog</a> |
| 26 | </p> |
| 27 | |
| 28 | <!-- ─────────────────────────────────────────────────────────────────────────── |
| 29 | DEMO: the single highest-leverage thing on this page for a *visual* tool. |
| 30 | Record a 15–25s screen capture of clawdcursor driving a real app end-to-end |
| 31 | (open app → find a field by name → type → verify), export to docs/demo.gif, |
| 32 | and uncomment the block below (it will sit right under the hero). |
| 33 | |
| 34 | <p align="center"> |
| 35 | <img src="docs/demo.gif" width="760" alt="clawdcursor driving a desktop app"> |
| 36 | <br><em>Opening an app, finding a field by name, typing, and verifying the result — accessibility-first, locally.</em> |
| 37 | </p> |
| 38 | ─────────────────────────────────────────────────────────────────────────── --> |
| 39 | |
| 40 | --- |
| 41 | |
| 42 | ## What it is |
| 43 | |
| 44 | Clawd Cursor is a **local MCP server** that gives any tool-calling agent — Claude Code, Cursor, Windsurf, OpenClaw, the Claude Agent SDK, or your own loop — safe control of the **real desktop**. It clicks, types, reads the screen, opens apps, and drives any GUI the way a human would: native apps, the browser, even a canvas. |
| 45 | |
| 46 | Most "let an agent use the computer" tools take a screenshot and feed it to a vision model — slow, expensive, and brittle. Clawd Cursor **compiles the screen into one UI map**: it fuses the accessibility tree and OCR into a confidence-scored set of elements, each tagged with a stable `el_NN` id, and acts on elements by id — not pixel coordinates. Coordinates appear only in the last-resort screenshot/vision tier (live pixels off the current frame), for canvas-only apps or tasks that genuinely need spatial reasoning. The result is cheaper, faster, private, and — uniquely — it **checks that each action actually did what it claimed**. |
| 47 | |
| 48 | > **If a human can do it on a screen, your agent can too.** No API, no integration, no problem — only the right sequence of reads, clicks, keys, and waits. Use it as the **last-mile fallback**: native API exists? Use it. CLI? Use it. Clawd Cursor is for the click, the legacy app, the GUI with no public surface. |
| 49 | |
| 50 | --- |
| 51 | |
| 52 | ## Why it's different |
| 53 | |
| 54 | The desktop-agent space is crowded. The closest **install-and-go** peers are [Windows-MCP](https://git |