Xpersona
Claim this agent
Agent DossierCLAWHUBSafety 84/100

Xpersona Agent

clawd-cursor

AI desktop agent that controls Windows/Mac natively via @nut-tree-fork/nut-js. Gives your agent eyes and full cursor control — direct screen capture, mouse clicks, keyboard input, drag operations, and GUI automation. Use when the user wants desktop automation, native AI control, or GUI testing. No external server required. Requires: AI API key (Anthropic or OpenAI) for vision features. Installs: Node.js dependencies via npm. Privacy note: screenshots are sent to AI provider APIs (Anthropic/OpenAI) for vision processing. --- name: clawd-cursor version: 0.4.1 description: > AI desktop agent that controls Windows/Mac natively via @nut-tree-fork/nut-js. Gives your agent eyes and full cursor control — direct screen capture, mouse clicks, keyboard input, drag operations, and GUI automation. Use when the user wants desktop automation, native AI control, or GUI testing. No external server required. Requires: AI API key (Anthropic or OpenAI)

OpenClaw · self-declared
Trust evidence available
View on ClawHub
clawhub skill install skills:amrdab:clawd-cursor

Overall rank

#62

Adoption

No public adoption signal

Trust

Unknown

Freshness

Feb 25, 2026

Freshness

Last checked Feb 25, 2026

Best For

clawd-cursor is best for click, too workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, CLAWHUB, runtime-metrics, public facts pack

OverviewEvidence & TimelineArtifacts & DocsAPI & ReliabilityMedia & RelatedMachine Appendix

Overview

Key links, install path, reliability highlights, and the shortest practical read before diving into the crawl record.

Verifiededitorial-content

Overview

Executive Summary

AI desktop agent that controls Windows/Mac natively via @nut-tree-fork/nut-js. Gives your agent eyes and full cursor control — direct screen capture, mouse clicks, keyboard input, drag operations, and GUI automation. Use when the user wants desktop automation, native AI control, or GUI testing. No external server required. Requires: AI API key (Anthropic or OpenAI) for vision features. Installs: Node.js dependencies via npm. Privacy note: screenshots are sent to AI provider APIs (Anthropic/OpenAI) for vision processing. --- name: clawd-cursor version: 0.4.1 description: > AI desktop agent that controls Windows/Mac natively via @nut-tree-fork/nut-js. Gives your agent eyes and full cursor control — direct screen capture, mouse clicks, keyboard input, drag operations, and GUI automation. Use when the user wants desktop automation, native AI control, or GUI testing. No external server required. Requires: AI API key (Anthropic or OpenAI) Capability contract not published. No trust telemetry is available yet. Last updated 4/15/2026.

No verified compatibility signals

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Feb 25, 2026

Vendor

Openclaw

Artifacts

0

Benchmarks

0

Last release

Unpublished

Install & run

Setup Snapshot

clawhub skill install skills:amrdab:clawd-cursor
  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence & Timeline

Public facts grouped by evidence type, plus release and crawl events with provenance and freshness.

Verifiededitorial-content

Public facts

Evidence Ledger

Vendor (1)

Vendor

Openclaw

profilemedium
Observed Apr 15, 2026Source linkProvenance
Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium
Observed Apr 15, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Events

Release & Crawl Timeline

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts & Docs

Parameters, dependencies, examples, extracted files, editorial overview, and the complete README when available.

Self-declaredCLAWHUB

Captured outputs

Artifacts Archive

Extracted files

0

Examples

3

Snippets

0

Languages

typescript

Parameters

Executable Examples

bash

git clone https://github.com/AmrDab/clawd-cursor.git
cd clawd-cursor
npm install && npm run build

env

AI_API_KEY=sk-ant-api03-...
AI_PROVIDER=anthropic

bash

# Computer Use (Anthropic — recommended for complex tasks)
npm start -- --provider anthropic

# Action Router (OpenAI/offline — fast for simple tasks)
npm start -- --provider openai

Editorial read

Docs & README

Docs source

CLAWHUB

Editorial quality

ready

AI desktop agent that controls Windows/Mac natively via @nut-tree-fork/nut-js. Gives your agent eyes and full cursor control — direct screen capture, mouse clicks, keyboard input, drag operations, and GUI automation. Use when the user wants desktop automation, native AI control, or GUI testing. No external server required. Requires: AI API key (Anthropic or OpenAI) for vision features. Installs: Node.js dependencies via npm. Privacy note: screenshots are sent to AI provider APIs (Anthropic/OpenAI) for vision processing. --- name: clawd-cursor version: 0.4.1 description: > AI desktop agent that controls Windows/Mac natively via @nut-tree-fork/nut-js. Gives your agent eyes and full cursor control — direct screen capture, mouse clicks, keyboard input, drag operations, and GUI automation. Use when the user wants desktop automation, native AI control, or GUI testing. No external server required. Requires: AI API key (Anthropic or OpenAI)

Full README

name: clawd-cursor version: 0.4.1 description: > AI desktop agent that controls Windows/Mac natively via @nut-tree-fork/nut-js. Gives your agent eyes and full cursor control — direct screen capture, mouse clicks, keyboard input, drag operations, and GUI automation. Use when the user wants desktop automation, native AI control, or GUI testing. No external server required. Requires: AI API key (Anthropic or OpenAI) for vision features. Installs: Node.js dependencies via npm. Privacy note: screenshots are sent to AI provider APIs (Anthropic/OpenAI) for vision processing. metadata: openclaw: requires: env: - AI_API_KEY bins: - node - npm primaryEnv: AI_API_KEY install: - git clone https://github.com/AmrDab/clawd-cursor.git - cd clawd-cursor && npm install && npm run build privacy: - Screenshots sent to external AI provider (Anthropic/OpenAI)

Clawd Cursor

One skill, multiple endpoints. Instead of integrating dozens of APIs, give your agent a screen. Gmail, Slack, Jira, Figma — if you can click it, your agent can too. Desktop automation skill for OpenClaw via native OS-level control.

Required Credentials

| Variable | Sensitivity | Purpose | |----------|------------|---------| | AI_API_KEY | High — enables external API calls | Anthropic or OpenAI key for vision/planning |

Privacy: Screenshots of your desktop are sent to the configured AI provider (Anthropic or OpenAI) for processing. Only use on machines without sensitive data visible, or in a sandbox/VM.

Optional variables: AI_PROVIDER (anthropic|openai)

Installation

Requires Node.js 20+.

git clone https://github.com/AmrDab/clawd-cursor.git
cd clawd-cursor
npm install && npm run build

No external server or setup script required — native desktop control works out of the box.

Configuration

Create .env in project root:

AI_API_KEY=sk-ant-api03-...
AI_PROVIDER=anthropic

Running

# Computer Use (Anthropic — recommended for complex tasks)
npm start -- --provider anthropic

# Action Router (OpenAI/offline — fast for simple tasks)
npm start -- --provider openai

Execution Paths

Path A: Computer Use API (Anthropic)

Full task → Claude with native computer_20250124 tools → screenshots, plans, executes autonomously. Best for complex multi-app workflows. ~100–156s. Very reliable.

Path B: Decompose + Route (OpenAI/Offline)

Task → subtasks → UI Automation tree → direct element interaction. Zero LLM for common patterns. Best for simple tasks. ~2s. Works offline.

Safety Tiers

| Tier | Actions | Behavior | |------|---------|----------| | 🟢 Auto | Navigation, reading, opening apps | Runs immediately | | 🟡 Preview | Typing, form filling | Logs before executing | | 🔴 Confirm | Sending messages, deleting, purchases | Pauses for /confirm approval |

API Endpoints

http://localhost:3847

| Endpoint | Method | Description | |----------|--------|-------------| | /task | POST | {"task": "Open Chrome"} | | /status | GET | Agent state | | /confirm | POST | {"approved": true} | | /abort | POST | Stop current task |

Security Considerations

  • Screenshots are NOT saved to disk by default. They are held in memory only and sent to the AI provider for processing. Use --debug flag to enable disk saves for troubleshooting.
  • AI API keys allow sending screenshots to external APIs — use scoped/temporary keys, rotate after testing.
  • The Express API binds to 127.0.0.1 only — not accessible from other machines on the network.
  • The /confirm endpoint enforces the 🔴 safety tier for destructive actions (send messages, delete files, purchases).
  • Run in a sandbox or VM when testing with sensitive data visible on screen.
  • No postinstall scripts — npm install only fetches dependencies, no code runs automatically.

Changelog

v0.4.1

  • Security: screenshots no longer saved to disk — held in memory only, sent to AI provider, then discarded
  • Debug saves opt-in via --debug flag
  • Localhost-only API binding documented
  • Cleaned 2,857 lines of dead VNC code

v0.4.0

  • Native desktop control via @nut-tree-fork/nut-js — no VNC server required
  • 17× faster screenshots (~50ms vs ~850ms)
  • 5× faster connect time (~38ms vs ~200ms)
  • Simplified onboarding: npm install && npm start

v0.3.3

  • Bulletproof headless setup — setup.ps1 runs end-to-end in non-interactive shells

v0.3.0

  • 6 performance optimizations (~70% faster task execution, 90% fewer redundant LLM calls)

v0.2.0

  • Anthropic Computer Use API as primary execution path
  • Action Router (zero-LLM) for simple tasks

API & Reliability

Machine endpoints, contract coverage, trust signals, runtime metrics, benchmarks, and guardrails for agent-to-agent use.

MissingCLAWHUB

Machine interfaces

Contract & API

Endpoints

Dossier APISnapshot APIContract APITrust API

Contract coverage

Status

missing

Auth

None

Streaming

No

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.
Invocation examples
curl -s "https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/snapshot"
curl -s "https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/contract"
curl -s "https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/trust"

Operational fit

Reliability & Benchmarks

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.
No benchmark suites or observed failure patterns are available.

Media & Related

Public screenshots, demo and owner links, plus neighboring agents from the same ecosystem for shortlist building.

Missingno-media

Visual context

Media & Demo

No screenshots, media assets, or demo links are available.

Comparison set

Related Agents

GITHUB_REPOSactivepieces

Rank

70

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Traction

No public download signal

Freshness

Updated 2d ago

OPENCLAW
GITHUB_REPOScherry-studio

Rank

70

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW
GITHUB_REPOSAionUi

Rank

70

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

Traction

No public download signal

Freshness

Updated 6d ago

MCPOPENCLAW
GITHUB_REPOSCopilotKit

Rank

70

The Frontend for Agents & Generative UI. React + Angular

Traction

No public download signal

Freshness

Updated 23d ago

OPENCLAW
Agent hubMore from this sourceOpenClaw agents

Machine Appendix

Raw contract, invocation, trust, capability, facts, and change-event payloads for machine-side inspection.

MissingCLAWHUB

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "CLAWHUB",
      "generatedAt": "2026-04-17T02:19:06.718Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "click",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "too",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:click|supported|profile capability:too|supported|profile"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Openclaw",
    "href": "https://github.com/openclaw/skills/tree/main/skills/amrdab/clawd-cursor",
    "sourceUrl": "https://github.com/openclaw/skills/tree/main/skills/amrdab/clawd-cursor",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T00:45:39.800Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-04-15T00:45:39.800Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/clawhub-skills-amrdab-clawd-cursor/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Sponsored

Ads related to clawd-cursor and adjacent AI workflows.