A9T9/RPA

JavaScriptui.vision

代替: UiPathAutomation AnywhereBlue Prism

Ui.Vision Open-Source RPA Software with Computer Vision, OCR, Anthropic Computer Use/LLM. Selenium IDE import/export.

web-automationselenium-ideimacrosbrowser-extensionbrowser-automationdata-driven-testsweb-scrapinganthropicanthropic-claudecomputer-use
スター成長
スター
2k
フォーク
407
週間成長
+11
Issue
0
5001k1.5k2k
2017年8月2020年8月2023年8月2026年9月
成果物npm
README

Ui.Vision RPA

  • Modern Robotic Process Automation, Selenium IDE compatible
  • Ui.Vision is open-source and free for personal and commercial use.

Questions? Suggestions? - Meet us in the Ui.Vision RPA user forum.

Every user benefits from the questions and answers provided in the forum, that is why we would ask you to post the question in the RPA forum first if a public forum is appropriate for your question. The forum is monitored by active users, tech support and the developers, so we would like to concentrate the discussion "over there" in one place.

How to install Ui.Vision:

Ui.Vision RPA for Chrome, Edge and Firefox is modern cross-platform RPA software for macOS, Linux and Windows. It includes a Selenium IDE and Web Macro Recorder. You find the latest version always in the Chrome and Firefox stores. You can use it completely free for private and commercial purposes:

The new uiv.* JavaScript API and the AI system prompt

Besides the classic command table, macros can be written as modern JavaScript using the uiv.* API - DOM and visual finders (uiv.$, uiv.findImage, uiv.ocr.findText, uiv.ai.find), the input tiers (uiv.page.*, uiv.browser.*, uiv.desktop.*), screenshots, tabs, CSV and downloads. Every call auto-waits and throws a real JS exception on failure, so try/catch works.

  • The Ui.Vision AI system prompt - the complete uiv.* API reference plus the automation recipes the AI assistant works from. This is the same text the AI in the side panel uses, and it is the best hand-written reference for the JS API. You can override it in Settings > AI > System Prompt.

  • llms-full.txt - the same material as one plain-text file, for feeding into an AI assistant.

  • MCP bridge - lets Claude Code and other MCP clients create, edit and run Ui.Vision macros in your browser. Source and setup: mcp/README.md.

  • uiv-commands.md (in this repo) - maps every classic command-table command to its uiv.* equivalent, or to the uiv.run('command', 'target', 'value') legacy bridge where no native method exists yet.

The published prompt page is generated from the source of truth in src/services/ai/macro_agent/service.ts via npm run gen:ai-prompt-page, so run that at release time to keep it in sync.

Building the Chrome, Edge and Firefox Extension

Building the extension is not required if you "only" want to use it.

You can install UI.Vision directly from the Chrome, Edge or Firefox stores, which is the easiest and the recommended way of using the Ui.Vision RPA software. Older versions can be found in the RPA software archive.

The information below is only required and intended for developers:

The project uses Node V20.11.1 and NPM V10.2.4

If you have any questions, please contact us at TEAM AT UI.VISION - Thanks!

To build the extension bundle

npm i -f
npm run build
npm run build-ff

npm run build creates the Chrome/Edge build in dist, npm run build-ff creates the Firefox build in dist_ff.

To develop

npm i -f
npm start

Use npm run start-ff for the Firefox variant. Both run webpack in watch mode, so the bundles in dist (Chrome/Edge) and dist_ff (Firefox) are rebuilt on every change.

Once done, the ready-to-use extension code appears in the /dist directory (Chrome, Edge) or /dist_ff directory (Firefox). Load it via chrome://extensions → "Load unpacked" (Chrome/Edge) or about:debugging → "Load Temporary Add-on" (Firefox).

Repository layout

  • src/ - the extension source (React UI, side panel, macro player, commands)
  • extension/ - static extension assets and manifest.json (Manifest V3)
  • mcp/ - the Ui.Vision MCP bridge, which lets Claude Code and other MCP clients create, edit and run macros. See mcp/README.md
  • dist/, dist_ff/ - build output for Chrome/Edge and Firefox
関連リポジトリ
feder-cr/AIHawk

Open-source AI browser agent for web automation: a web browsing agent and computer-use agent in plain English. Browser MCP for Claude Code and Gemini CLI.

PythonPyPIMIT Licenseai-agentautonomous-agents
github.com/feder-cr/AIHawk/wiki
30.3k4.6k
browser-use/browser-harness

Browser Harness | Self-healing harness that enables LLMs to complete any task.

PythonPyPIMIT Licenseai-agentbrowser-agent
browser-harness.com
17.4k1.7k
nanobrowser/nanobrowser

Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.

TypeScriptnpmappApache License 2.0aichrome-extension
nanobrowser.ai
13.8k1.4k
seleniumbase/SeleniumBase

APIs for browser automation, testing, and bypassing bot-detection. Includes CDP Mode: A stealthy configuration for chromium that passes every bot detection test.

PythonPyPIMIT Licensepythonselenium
seleniumbase.io
13k1.6k
g1879/DrissionPage

Python based web automation tool. Powerful and elegant.

PythonPyPIlibraryOtherautomation-frameworkpython
drissionpage.cn
12.4k1.2k
mherrmann/helium

Lighter web automation with Python

PythonPyPIlibraryMIT Licenseseleniumselenium-python
8.3k512
Kaliiiiiiiiii-Vinyzu/patchright

Undetected version of the Playwright testing and automation library.

TypeScriptnpmlibraryApache License 2.0automationbot
playwright.dev
4.4k219
lackeyjb/playwright-skill

General-purpose Playwright automation for coding agents

JavaScriptnpmskillMIT Licenseagent-skillsai-agents
3.1k240
automagica/automagica

AI-powered Smart Robotic Process Automation 🤖

PythonPyPIlibraryrparobot
automagica.com
3.1k485
saifyxpro/HeadlessX

The undetected self-hosted browser automation platform. Powered by Camoufox (Firefox) for 0% detection rates. Built for speed, privacy, and scalability.

TypeScriptnpmOtherautomationbrowser-automation
headlessx.saify.me
2.3k276
tinyfish-io/tinyfish-cookbook

A collection of sample apps and recipes built with the TinyFish web agent. Open-source examples for you to learn & build!

TypeScriptnpmtutorialMIT Licenseagentagentic
tinyfish.ai
2.2k329
vibheksoni/stealth-browser-mcp

The only browser automation that bypasses anti-bot systems. AI writes network hooks, clones UIs pixel-perfect via simple chat.

PythonPyPIMIT Licenseai-agent-toolsai-tools
1.9k274