What makes Open Computer Use notable?

1K downloads. Trust evidence available

How should Open Computer Use be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Open Computer Use

Guidance for installing, configuring, and operating Open Computer Use, an open-source Computer Use MCP service for macOS, Linux, and Windows. Skill: Open Computer Use Owner: ifuryst Summary: Guidance for installing, configuring, and operating Open Computer Use, an open-source Computer Use MCP service for macOS, Linux, and Windows. Tags: claude:0.1.0, codex:0.1.0, computer-use:0.1.0, desktop-automation:0.1.0, gemini:0.1.0, latest:0.1.0, mcp:0.1.0 Version history: v0.1.0 | 2026-05-14T10:47:53.999Z | user Initial ClawHub publish Archive index: Archive v0.1.0:

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

0.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 0.1.0release · observed May 14, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1756vbgvfm4qb4461jpyb0vk186p8kx:open-computer-use

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

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-ifuryst-open-computer-use/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

5,497 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: open-computer-use
description: Guidance for installing, configuring, and operating Open Computer Use, an open-source Computer Use MCP service for macOS, Linux, and Windows.
---

# Open Computer Use

## Overview

Open Computer Use is an open-source Computer Use service exposed through MCP. It lets compatible AI agents operate local desktop apps on macOS, Linux, and Windows through tools such as `list_apps`, `get_app_state`, `click`, `type_text`, `press_key`, `scroll`, `drag`, and `set_value`.

Use this skill when a user wants to install, configure, verify, troubleshoot, or operate Open Computer Use from an agent runtime such as Codex, Claude Code, Gemini CLI, opencode, or another MCP client.

## Install

Install the CLI:

```sh
npm i -g open-computer-use
```

On macOS, run it once and grant Accessibility and Screen Recording permissions:

```sh
open-computer-use
```

Windows and Linux do not require the macOS permission step.

## MCP Setup

Install into Codex:

```sh
open-computer-use install-codex-mcp
```

Or configure any MCP client manually:

```json
{
  "mcpServers": {
    "open-computer-use": {
      "command": "open-computer-use",
      "args": ["mcp"]
    }
  }
}
```

## Other Agent Integrations

Open Computer Use also includes installer commands for common agent runtimes:

```sh
open-computer-use install-codex-plugin
open-computer-use install-claude-mcp
open-computer-use install-gemini-mcp
open-computer-use install-opencode-mcp
```

## Direct CLI Calls

Use the CLI to call one tool:

```sh
open-computer-use call list_apps
open-computer-use call get_app_state --args '{"app":"TextEdit"}'
```

Run a sequence in one process so element indexes can be reused:

```sh
open-computer-use call --calls '[{"tool":"get_app_state","args":{"app":"TextEdit"}},{"tool":"press_key","args":{"app":"TextEdit","key":"Return"}}]'
```

Check setup and permissions:

```sh
open-computer-use doctor
```

## Operating Rules

- Treat Computer Use as control over the user's real desktop session.
- Ask before actions that send messages, submit forms, delete data, install software, change system settings, make purchases, or expose sensitive local information.
- Prefer accessibility element indexes from `get_app_state` over coordinate clicks when available.
- Re-read app state after important actions before continuing.
- On macOS, if tools fail due to permissions, ask the user to grant Accessibility and Screen Recording for the Open Computer Use app or runtime process.

## Project Links

- Repository: https://github.com/iFurySt/open-codex-computer-use
- npm package: https://www.npmjs.com/package/open-computer-use

_meta.json

{
  "ownerId": "kn7ckr2v4a5w1wwvsrk32m3nk586pa1b",
  "slug": "open-computer-use",
  "version": "0.1.0",
  "publishedAt": 1778755673999
}

skill-card.md

## Description:

Guidance for installing, configuring, and operating Open Computer Use, an open-source Computer Use MCP service for macOS, Linux, and Windows.

This skill is ready for commercial/non-commercial use.

## Publisher:

[ifuryst](https://clawhub.ai/user/ifuryst)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent users use this skill to install, configure, verify, troubleshoot, and operate the Open Computer Use MCP service from compatible agent runtimes.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill configures a desktop-control MCP tool with broad access to the user's local computer session.

Mitigation: Install only trusted package and repository versions, grant OS permissions only when needed, and revoke permissions or remove MCP/plugin configuration when no longer used.

Risk: Desktop automation can send messages, submit forms, delete data, install software, change system settings, make purchases, or expose sensitive local information.

Mitigation: Require user approval before sensitive actions and re-read application state after important actions before continuing.

## Reference(s):

- [Open Computer Use ClawHub page](https://clawhub.ai/ifuryst/skills/open-computer-use)
- [Open Computer Use repository](https://github.com/iFurySt/open-codex-computer-use)
- [open-computer-use npm package](https://www.npmjs.com/package/open-computer-use)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown with shell commands, JSON configuration examples, and operating guidance]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Includes safety guidance for desktop-control permissions and MCP/plugin configuration.]

## Skill Version(s):

0.1.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

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!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

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

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.