Havuz

A business question goes in. A consulting-grade deck comes out. Four composable skills for Claude Code and Codex: strategy storyboarding, br

Turn any website into a CLI/API for AI agents

Local self-hosted Meta Ad Library research tool: deep keyword/advertiser scraping, saved-ad swipe files, Hook Lab trend-stage intelligence,

Beautiful screen recordings, made by your favorite AI agent.

From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.

Automation-ready anti-detect browser workspace with isolated profiles, REST API, MCP, Docker, and Playwright control.

Grabs all your Perplexity conversations data, spits it out into a nice file folder structure and allows you to find your old conversations a

Testing skills for AI coding agents: evidence-backed strategy, executable cases, Playwright/API testing, regression and QA memory. 面向 AI Age

闲鱼卖家 RPA 自动化运营助手｜多店铺聚合接待·订单自动处理·AI智能客服

A learning-first, local-first career workspace & job application automation engine. Tailors resumes, applies across Naukri, Wellfound, Insta

34 个核心 Demo + 3 个附录，覆盖前端工程化全链路：pnpm/Vite/ESLint/Husky、分包懒加载、CI/CD、Vitest/Playwright、性能监控、请求池/重试、Service Worker、AI 辅助 PR Review、知识图谱可视化、VS Co

Open-source SEO audit agent — real-browser checks, backlink scoring, and multi-engine AI citation tracking (Claude, ChatGPT, Gemini, Perplex

CLI tool to search, filter and manage job opportunities using customizable rules and local persistence.

Find memory leaks in your single-page web app in minutes rather than hours, with Playwright.

Save Scribd documents and embeds as PDF files for offline reading.

Record any browser page as GIF or video via MCP — powered by Playwright + ffmpeg

Claude Code skill: a background Playwright browser for screenshots (desktop/tablet/mobile), frontend health checks, visual diffs, scripted U

英语词根记忆短视频生成器：一条线 + 一颗球，把词根演成 9:16 记忆短片（design table → SVG 动画 → edge-tts → 逐帧渲染 → 五道校验）

An open-source travel agent that works on real websites: plan trips, book in a browser beside the chat, stop at the payment page. Desktop ap

Generate professional README.md with 16:9 infographics, SEO-optimized metadata, and structured author sections — powered by Playwright and A

Open-source statement-level Playwright tracer, purpose-built for AI agents. Analyzes test runs with increased accuracy.

Agent-friendly local publisher for Xiaohongshu, Douyin and WeChat Channels with multi-account safety, scheduling and deduplication.

Clone any website into a pixel-accurate Next.js app with AI — Playwright-measured extraction (no eyeballing), spec-gated parallel builder ag

QA agent swarms. Test web apps autonomously with greater speed and accuracy. Visual navigation, real workflows, evidence-backed reports.

One beautiful HTML test report for Playwright, Cypress and WebdriverIO, with Cucumber BDD. Shows what broke, who owns it and whether it is n

The intelligence layer for any web scraper. Pair with Scrapling, Playwright, or httpx to crawl smarter.

An MCP server for parallel browser automation by AI agents with multiple cloud providers

OpenAI- and Anthropic-compatible API for Duck.ai, driven by a real Chrome browser via Playwright. Streaming chat, image generation, session

A portable, self-improving SDLC harness for agent fleets — plan → issues → build → test → review → UX-eval → security → ship, on any runtime

A disposable copy of your production stack for every pull request: masked Postgres, contained third-party APIs, and agents that use your app

领域无关的多 agent UI 自动化测试编排骨架，用 Claude Code 驱动「探索页面→设计用例→写测试→审查」流水线

端到端 QA 验收编排器 · Agent Skill：上下文 → 风险 → 用例 → 脚本 → 执行 → 审查 → 报告，全程自动衔接，只在用例确认时停下等你审核。支持 Claude Code / Codex / Cursor

A Chromium fork built for AI agents: built-in MCP server, per-agent logged-in identities, sessions as tab groups

Advanced Windows & Web Automation Tool. Features: Record Clicks/Scrolls, Anti-ban (Random Delay), Playwright integration, and OCR.

🐟 闲鱼/Goofish 智能监控控制台：AI 大模型选品 + 收藏降价·售罄即时提醒，全本地运行不外传。Xianyu second-hand deal monitor — LLM-filtered picks, price-drop & sold-out alerts, dea

Get to Danish housing listings first — rentals and for-sale, multi-site watcher with instant phone push alerts

Self-hostable, MCP-native testing platform. Manual test management, deterministic runs, optional AI. Your stack, your LLM, your data.

High-performance OpenAI & Anthropic compatible API gateway for Qwen with multi-account rotation, interactive TUI dashboard, and resilient to

A dashboard for your browser tests (Playwright, Vitest, Storybook), across projects and over time

Let Claude Code, Codex, OpenCode, Pi and other agents run DeepSeek Harness (dsh) sessions in parallel: research batches, material gathering,

抖音直播弹幕中台 (Douyin Live Danmaku Hub)：双采集内核（浏览器+CDP / 轻量直连）、多房间并发、WS/SSE/Webhook 三通道分发、可视化控制台、Docker 一键部署

Open-source runtime for grounded, model-agnostic computer-use agents with verifiable action receipts.

Forge Agent is a free, autonomous AI coding agent that requires no API key or subscription. It uses browser automation to communicate with a

Rebuild a local twin of your app on every push, replay approved business journeys, and report a GitHub check.

Open-source AI operations platform for cross-border commerce: product collection, drafts, AI content optimization, publishing, and order/inv

🐮 牛来动画生成器 —— 输入一段小故事，一条命令产出还原电影《牛来》风格的抽象动画：无厘头台词、严格同步的字幕与配音、粗糙低模的直立牛。Three.js 程序化 3D 渲染 + DeepSeek 剧本生成 + TTS 配音 + FFmpeg 合成，不依赖视频大模型。AI vid

An AI-powered crypto X (Twitter) reply-guy bot: a live tweet feed feeds a scoring engine, an LLM (Claude or OpenAI) writes the reply in a co

AI side-panel assistant for Chrome. Reads the active page and acts on it with your approval — click, type, switch tabs, fill forms. Multi-LL

AI 測試大師 — MCP server driving pytest / Jest / Cypress / Go / Maestro. Analyze, generate, run, advise. Web + Mobile (iOS/Android/BlueStacks).

Automated Qoder account registration with temp mail, captcha solving, and 9Router integration