Caishi
Local installio.github.ZhongQuinnKing/caishi
Read Bilibili, Douyin, Xiaohongshu and any web page via your own logged-in Chrome.
Resumable browser, API and MCP workflows for AI agents. Verify CSV/Excel batches locally.
Self-hosted stealth browser for AI agents: Firefox engine + Rust MCP runtime.
Zero-dependency browser automation over raw CDP — no Puppeteer, Playwright, or Selenium.
MCP server and Firefox add-on that let an AI agent drive your real, logged-in browser. Free tier.
Website screenshots for AI agents: full-page, country proxies, ad & cookie-banner removal
AI browser automation. Write async Python to navigate, click, type, and extract data.
Hand browser work off to a server-side agent: read the page as a table, act, then verify.
Flashless macOS & Windows native computer-use engine for AI vision, mouse & keyboard automation
MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
Secure Linux desktop automation - input, screen/OCR/vision, AT-SPI2 UI tree, window, clipboard
Real signed-browser automation for AI agents, over a local stdio MCP server.
Verified desktop control for agents on Windows and Linux: apps with no API, windows, shell, browser.
Agents use real GNOME/Wayland apps: on your screen, or an invisible second desktop you never see
See any site as it looks on a real iPhone, iPad or MacBook — and drive that window over MCP.
MCP server that drives the real Chrome you already use, through an extension and CDP.
Drive your real, logged-in Chrome from any MCP client — even from a remote machine, no inbound port.
Local browser automation for MCP clients powered by DrissionPage.
Drive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent.
Drives a real Chromium browser: navigate, click, type, read pages, OCR, QR, network capture
Browser sessions, checkpoints, rewind, fork, lineage, and lifecycle tools for brawsr.
Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
Source-grounded web research: search, extraction, verification, and browser automation.
Archive any URL to a shareable rrweb/pdf/png snapshot + agent-driven web QA (scan, run E2E flows).
QA agent for vibecoded apps. Real browser checks, your AI fixes them. Ship to green.
Turn Mac apps into MCP tools via the accessibility API: no screenshots, no model per step.
smartfetch direct-URL fetch, smartsearch web search, smartcrawl, smartbrowser local browser actions.
Capture a web page from your own Chrome as a PDF whose text is still text.
Job search and form filling; dry run by default, real submits need your approval or consent.
Open HTML reports in the browser and edit them live while the person watches, or by hand.