OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Browser Agents

Webcmd

Webcmd is browser automation infrastructure for AI agents, combining live browser controls with a learning memory layer that records useful website navigation context locally for reuse on later runs.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Webcmd — OpenViST project profile in Browser Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Webcmd when an AI agent needs to operate websites through a real browser, especially when navigation learned during one task can help with later tasks.

Who it is for

  • Developers configuring browser automation for AI agents.
  • Agent builders who repeat research or information-gathering tasks across websites.
  • Teams using browser agents with authenticated profiles and separate browser sessions.

Documented uses

  • Inspect pages, click, type, extract content and capture network calls through a real browser.
  • Reuse observed site navigation context across later agent runs.
  • Collect and summarize information from research, community, social, shopping and booking websites.
  • Run local multi-step browser exploration through a sandboxed Playwright-style program attached to a browser session.
Before you choose

Requirements & limits

The documented manual setup requires Node.js 20.6 or later and installs the CLI package through npm. The repository identifies the project as open source under Apache-2.0.

  • Webcmd separates live browser control from the memory layer that records observed navigation context.
  • The live browser remains the source of truth; memory failures are described as non-blocking.
  • Profiles store cookies, while sessions are independent browser windows within a profile; parallel agents should use separate sessions.
  • The documented manual setup adds a webcmd-browser skill to a selected supported harness or custom skills path.
  • The README's claim of up to 90% lower browser-agent token spend is a project claim, not an independently verified result in this profile.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Webcmd and add its browser skill

Install the Webcmd CLI and add the webcmd-browser skill to a supported harness or custom skills path.

Before you start

  • Node.js 20.6 or later
  • A supported harness such as Claude or Codex, or a custom skills path

Steps

  1. Install the package globally with npm install -g @agentrhq/webcmd.

  2. Run webcmd skills add.

  3. Choose a supported harness or provide a custom skills path when prompted.

Expected outcome

The webcmd-browser skill is installed for the selected harness or path; load or tag it when doing live browser work.

Guide limitations

  • This covers installation and skill setup only, not completing a browser task.
  • The project documentation lists supported harness choices but does not enumerate all of them here.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
10 October 2026
Original website title
agentrhq/webcmd · Official homepage title · retained in its source language
How we review sourcesSuggest a correction