Havuz

Beautiful screen recordings, made by your favorite AI agent.

Telegram-бот: следит за поиском на Авито и Wildberries и присылает новые объявления и снижение цен

Simulated users explore web apps, with replayable browser evidence.

Claude Code skill: faceless 9:16 explainer reels in a cut-paper style. Voice-timed scenes, word-by-word captions. Free, local, no API keys.

🎙️ Local, open-source voice agent that talks back AND acts (opens YouTube, searches, scrolls). Workshop starter: whisper + ollama + kokoro +

CRAB (Clean Rebuild of Anything's Behavior): rebuild software from behavior, not source code. An MCP-powered toolkit for black-box observati

Agent Skills that convert a WordPress site (or any live site) into a static Astro site with URL, SEO, content and pixel parity, then take it

Route AI web browsing through your home residential IP via Tailscale. Bypasses Cloudflare Turnstile, Amazon anti-bot blocks, and datacenter

One command. Any URL. Cloned, reverse-engineered, running.

Agent Skill + Playwright/axe-core verification loop that teaches AI coding agents to build accessible frontends on the first pass. Companion

Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.

Unofficial MCP server for Continente.pt: search products, check sale rules, read favorites and orders, and make verified cart changes from C

Multi-platform automated operation and publishing (Xiaohongshu / Douyin / TikTok / X / YouTube / WeChat Official Accounts) for Muse, Dots, a

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

Let AI agents use the software that has no API: back offices, intranets, dashboards, plus API files, spreadsheets and databases, as MCP tool

一句话让 AI 帮你做产品宣传片！把产品名或网址告诉 Cursor、Claude Code、Codex 等 AI 编程工具，它会自己调研产品、画出多种风格样图让你挑选、截取 4K 真实页面、按音乐节拍卡点剪辑、生成 AI 旁白并逐句转写校验、自动审图，最后交付一支 4K 商业宣传

Claude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA

Telegram inside Claude Code: read chats and channels in a pane, get AI summaries of unread posts. No API key, no bot.

Free, open-source anti-detect browser profile manager: per-profile fingerprint, cookies and proxy, Camoufox and Chrome engines, desktop app,

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

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

Open-source Agent Skill that turns a website, phone clips or a CSV into a finished short video: launch videos, promo reels and narrated expl

Self-hosted Google search scraper for Python. Scrape Google SERP results with a real Chrome browser and your own residential proxy. Self-hos

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

Claude Code plugin + skill: turn a short brief into a looping kinetic-typography launch video. One self-contained HTML file with a pure seek

LinkedIn iş ilanlarına gelen aday bilgilerini kendi Chrome oturumunuz üzerinden toplayıp MCP, yerel dashboard ve CSV/JSON dışa aktarımıyla erişilebilir kılar.

Neden yükseliyor · Ölçümlerde iki günlük yaşına rağmen 28 yıldız ve son 28 günde 27 commit görünüyor; bu, kısa vadeli ilgi ve yoğun geliştirmeye işaret ediyor. Ancak tüm commit'lerin tek yazardan gelmesi, ilginin veya bakım kapasitesinin geniş bir topluluğa yayıldığını göstermiyor.

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

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

Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwrig

🚀 AI 全链路求职自动化平台：抓取→清洗→AI评估→简历改写→自动投递，四大招聘平台 + 飞书 ChatOps 指挥 | Industrial-grade AI job-hunting automation: scrape → clean → LLM eval → resume

可观测、可评测、可部署的多 Agent 工程平台：结构化路由、Skills、工具/RAG、50 模型实验中心与 LLM-as-Judge。FastAPI + Vue。

An agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.

One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.

Local-first recruitment intelligence and application operations agent

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

Open-source AI agent testing framework for browser and native desktop apps, with explicit tool effects, evidence, lifecycle, and trace contr

aside-codemode, Aside içindeki JavaScript REPL üzerinden dosya araması ve browser işlerini tek çağrıda çalıştırıp modele yalnızca seçilmiş sonuçları döndürür.

Neden yükseliyor · 14 günlük yaşına karşılık 124 yıldız ve son 28 günde 287 commit görünmesi, hızlı bir başlangıç ve yoğun geliştirme faaliyetine işaret ediyor. README'deki ölçülebilir arama ve browser örnekleri de ilgiyi artırabilir; ancak yükselişin kesin nedeni bilinmiyor. Commit'lerin yalnızca 2 farklı yazardan gelmesi, faaliyetin geniş katılımla desteklendiğini göstermiyor.

Stealth antidetect browser for Playwright — patched Chromium 151 with C++ persona, persistent profiles, humanize & GeoIP. launch() in, Chrom

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

Record what a web app does — video, screenshots, runbook — by describing the flow to your coding agent. For UAT, hand-offs, bug reports, rev

One SaaS URL in, a due-diligence-grade platform teardown out. A Claude Code skill.

Measurement for coding agents building UI: extract a contract from the reference page, check the implementation, get numbers back

Agentic browser automation built from small, reusable pieces.

Unofficial Ozon MCP server for product search, prices, product cards, and reviews.

Code-based video generation. An open-source video pipeline for AI coding agents: a real browser captures your real product, and your agent d

Any website, within reach of any agent. Captures a site's native WebMCP tools and generates the bridge from the live DOM when there are none

Human escalation for Solari browser agents — hand off the live session, solve the blocker, resume in the same session.

Agentic E2E testing platform — natural-language test cases executed by a browser agent in real Chrome, judged by an LLM with video/screensho

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