Havuz

BossClaw｜本地 AI 求职助手与自动投递工具：覆盖 BOSS直聘 / 猎聘 / 智联招聘 / 前程无忧，简历解析 → 职业画像 → AI 岗位匹配排序 → 按岗位定制简历 → 生成招呼语并安全投递，全程可追踪；本地优先、独立运行不占用浏览器，支持外部 agent 经 MC

腾讯云 轻量应用服务器 4核4G 38元/年 抢购脚本

Persian-first UI/UX intelligence and RTL audit CLI for AI coding assistants

Production-grade Playwright + TypeScript Scaffold for Agentic Testing. Harness for all major AI coding agents baked in.

OpenClaw + 大模型驱动的完整电商客服自动化系统：覆盖淘宝、拼多多、抖音、快手、小红书、视频号，包含浏览器/手机 Worker、订单物流与售后工具、记忆、回执、恢复和 Eval。

Cloudflare Turnstile detection and bypass

A swarm of AI users that test your website in real browsers — visualized as a pixel-art aquarium. Live friction maps, multi-user scenes, up

Moli, web sayfalarını AI agent’lar için fetch etme, içerik çıkarma ve otomasyon amacıyla kullandıran Rust tabanlı bir headless browser’dır.

Neden yükseliyor · 48 günde 2442 yıldız ve son 28 günde 752 commit dikkat çekiyor; AI agent’lar için browser otomasyonu talebiyle örtüşüyor. Ancak 28 günlük commit’lerin tek farklı yazardan gelmesi, hareketliliğin geniş katkıcı tabanıyla desteklendiğini göstermiyor.

Free, open-source antidetect browser with its own open-source Firefox engine, Chromium support, unlimited profiles, Local mode, Cloud sync,

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

粘一条闲鱼链接，自动去水印、生成三版不重样的文案、搜补充图。Windows 桌面应用，装上就能用。

Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.

发现藏在前端代码里的 API，验证未授权访问风险 · 动态浏览器追踪 × JavaScript 静态分析

Self-hosted reCAPTCHA v3 solver and token harvester, Enterprise and standard, built on Playwright

MCP server that scrapes public posts from X, LinkedIn and Hacker News in a local browser that is never signed in

Claude Skill & CLI pipeline for creating, designing, and rendering deterministic, lightweight looping GIF infographics for LinkedIn (RTL & A

Randi Fajar Wicaksono’nun deneyim ve projelerini yayımlayan, içerik ve gizlilik kurallarını build aşamasında doğrulayan kişisel developer portfolio.

Neden yükseliyor · 55 günde 479 yıldız dikkat çektiğini gösteriyor; ancak bu veriler yükselişin nedenini açıklamıyor. README’deki test, içerik doğrulama ve gizlilik kontrolleri projeyi sıradan bir portfolio’dan daha özenli gösteriyor. Son 28 günde commit ve farklı yazar olmadığı için güncel geliştirme etkinliği görünmüyor.

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

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

Grok 批量注册 (Camoufox) + 实时 Web 监控面板 | Batch Grok registration engine with live panel — concurrency · ASN blacklist · proxy pool · token auth

Automate your job search with your favorite coding agent. Skills, guides, and scripts that any agent (Devin, Claude, Cursor, opencode) consu

Browser-authenticated Fetch and existing-browser Connect for AI agents — use Chrome or Edge login state with site adapters, agent-browser, B

WhatsApp Commune drives WhatsApp Web through browser automation, using Playwright engine to interact with the interface programmatically.

Claude Code skill for Dribbble-level product launch videos from code. One shape that never cuts, springs, a cursor that drives every change,

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

ChatGPT Web’deki modelleri, Codex’te MCP üzerinden görev bağlamı ve yerel araçlarla kullanılabilir hâle getiren bir launcher’dır.

Neden yükseliyor · ChatGPT Web modellerini Codex arayüzü ve araç akışıyla birleştirme vaadi, API/Codex kotası kullanmadan mevcut abonelikten yararlanmak isteyen geliştiriciler için somut bir ilgi alanı. 63 günlük yaşına karşılık 11.831 yıldız ve son 28 günde 92 commit ile 6 farklı yazar, README’deki iddialara ek olarak kayda değer ilgi ve yakın dönem aktivite gösteriyor; ancak bunlar tek başına güvenilirlik veya benimsenme kanıtı değil.

开源 AI 订阅商品公开报价聚合、分类与价格追踪平台

Not a chatbot. Not a coding assistant. A digital operator that controls your entire PC — 219 tools, screen perception, HID control, browser

Stateful execution layer for browser agents.

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

MCP server that drives Google Flow (Veo / Nano Banana) through its internal tRPC API, with a hard credit-cost gate

Visual testing for agents: uiverify CLI, Vitest/Playwright SDKs, and agent skills.

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

AI-native, source-available (PolyForm Perimeter) game-dev toolkit: bforge — deterministic headless-Blender asset forge for AI agents (138 op

Generate and download Google Flow videos and images from Codex, Antigravity, and any MCP agent. Live Omni, Veo, and Nano Banana capabilities

Control your real browser and ScriptCat from the CLI, AI clients (MCP) and scripts: tabs, browser data, page automation, debugging, raw CDP,

UniSearch 是一款基于 AI 的多平台公开内容采集与调研桌面工具。 通过自然语言描述调研目标，由 AI 自动规划任务流程，并发调度底层连接器进行公开数据采集与清洗。

Open-source AI browser agent for web reverse engineering. Turn websites into browser-free API clients and crawlers with CDP, network tracing

An autonomous multi-agent AI workspace that automates job hunting. Features native PDF parsing, ATS scoring, multi-engine job scraping, Play

Windows 下双击即用的 Grok（xAI）账号自动注册面板 - 浏览器自动化注册、SSO→CPA 转换、多邮箱源支持、多格式导出

Lightweight stealth-oriented browser MCP server in Rust — one shared Chrome for many AI agents, 64+ Playwright-style tools, no Node.js runti

Fly the web on a string — a lightweight (~7MB) Rust browser-automation MCP server for AI agents. Streamable HTTP, 21 tools, HTML→PDF, plus a

Stealth headless browser engine in Rust. Real V8 + DOM, Chrome TLS fingerprint, solves Cloudflare without Chromium.

Design cognition loop for Codex, Claude Code, and Pi-compatible agents — frame, diverge, see, reframe

🎭 Self-hosted anti-detect browser manager with three engines per profile - Camoufox (stealth Firefox), Chromium, and real Android - plus coh

The Regression Testing Framework for AI Agents. Replay · Evaluate · Assert · Catch Regressions — in CI. Like Jest for your AI layer.

Claude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.

MCP server para el CENDOJ 🇪🇸 — Acceso automatizado a resoluciones judiciales de España, filtros avanzados de jurisprudencia y lectura de sen

코딩 에이전트가 만들어 주는 데모 영상 — 바이브코딩 결과물을 제대로 뽐내세요.

Your coding agent makes the demo video — a narrated, captioned MP4 from one storyboard.json. Deterministic replay re-renders it in CI (no ke