Open-Source-Browser-Automatisierungstools, installiert und ausgeführt

Lassen Sie Claude Code, Codex oder Cursor Ihr echtes Chrome verwenden, in dem Sie angemeldet sind. Ein Prompt zum Einrichten. Open source, MIT.

Was der Test ergab: browser-harness 0.1.13 installs from source, all 266 unit tests pass, and the CLI controls a headless Chromium via CDP, page_info, navigation, tab management, JS execution, and screenshots all work end-to-end. 12 Minuten.

Open-Source-Browser-API für AI Agents & Apps. Steel Browser ist eine komplett ausgestattete Browser-Sandbox, mit der Sie das Web automatisieren können, ohne...

Was der Test ergab: With a user-local Node 22 and Chrome for Testing plus DISABLE_CHROME_SANDBOX=true, the dev-mode API runs on port 3000, /v1/health returns 200 with live Chrome, and sessions/scrape/screenshot/pdf plus external CDP client connections all worked with real results. 11 Minuten.

Browser MCP ist ein Model Context Provider (MCP)-Server, der KI-Anwendungen ermöglicht, Ihren Browser zu steuern.

Was der Test ergab: All dependencies install, the project builds, typechecks, and all 252 tests pass across all 4 tested packages using real headless Chromium, and the MCP server binary responds to --help. 8 Minuten.

Deklarative Datenautomatisierungssprache und Go-Laufzeitumgebung für strukturierte Extraktions-Workflows.

Was der Test ergab: Go 1.27.1 installed, all dependencies resolved, all 68 test packages pass with race detection, CLI binary compiles and runs FQL queries end-to-end. 7 Minuten.

Playwright for Go, eine Browser-Automatisierungsbibliothek zur Steuerung von Chromium, Firefox und WebKit mit einer einzigen API.

Was der Test ergab: Playwright for Go is installed and functional: Playwright driver v1.62.1 launches Chromium 151.0.7922.34 in headless mode, all package tests (0 failures) and all integration test groups (0 failures) pass with real browser interactions including page navigation, DOM queries, locators, assertions, network interception... 42 Minuten.

Atomic Agent ist ein local-first AI agent. Führt Open-Weight-Modelle auf Ihrem eigenen Rechner über llama.cpp aus.

Was der Test ergab: Build compiles, CLI binary runs and responds to --version/--help, 594 of ~600+ test files pass with 1 genuine test-logic failure in sidecar send-message concurrency, and all 22 eval-memory test files pass. 58 Minuten.

Stealth-Browser-Automation für AI-Agenten über MCP und das Chrome DevTools Protocol: Navigation, Netzwerk-Hooks, DOM-Extraktion und pixelgenaues UI-Klonen.

Was der Test ergab: Stealth Browser MCP server runs on stdio transport, spawns a headless Chromium 157.0.8086.0, navigates to data URLs, extracts page HTML content, and closes cleanly -- all via MCP protocol over stdio. 15 Minuten.

Ein kleines, schnelles Rust CLI, das einen echten Browser über das Chrome DevTools Protocol steuert, entwickelt für coding agents.

Was der Test ergab: The browser-control CLI builds and passes all 10 unit tests; the binary connects to Chromium 127 over CDP and successfully executes open, snapshot, eval, cdp, text, and inspect commands against real web pages. 10 Minuten.

Selbstlernender Agent-Browser

Was der Test ergab: Webcmd 0.8.4 is installed, builds from source, runs unit tests (3571 passed), connects to Cloak browser daemon, and responds to CLI commands. 5 Minuten.

PHP-Webbrowser-Emulator-Abstraktion

Was der Test ergab: PHP 8.4.26 and Composer 2.10.3 are installed locally, all 38 dependencies are in vendor/, the Mink test suite passes 520 tests with 1165 assertions, composer.json validates, phpstan reports no errors, and a stub-driver script using the Mink library successfully found the Downloads link with href /download. 12 Minuten.

AIPex: KI-Browser-Automatisierungsassistent, keine Migration und Datenschutz an erster Stelle. Alternative zu Manus Browser Operator, Claude Chrome und Agent...

Was der Test ergab: Repository builds, typechecks, lints, format-checks, and runs 639 passing tests across 5 workspace packages (core, dom-snapshot, browser-runtime, aipex-react, browser-ext) plus the mcp-bridge package, using pnpm 12.10.1 on Node 20.19.0. 5 Minuten.

Chrome-Seitenleisten-Erweiterung, die es DeepSeek Harness ermöglicht, Ihren browser direkt zu bedienen, ohne dass visuelle Fähigkeiten erforderlich sind.

Was der Test ergab: The dsh-browser workspace pnpm-installs, builds, typechecks, and passes all 528 unit tests plus the real-DSH smoke test; the dsh web server starts, serves the UI at 200, exposes the bridge-config endpoint, authenticates via token→cookie exchange, and responds with correct RPC results via both the HTTP /api carrier and... 28 Minuten.

Scout: der Open-Source-Browser-Agent von Outcrawl. Automatisch gespiegelt aus Outcrawls eigenem Repository.

Was der Test ergab: Bun 1.4.3 and Node 22.14.0 installed locally, bun install succeeded, and every workspace test suite passes (1453 pass, 0 fail, 0 skip) including the previously-skipped real headless-Chromium tests; a standalone Scout run completed with status completed and data 'All stories loaded.'. 10 Minuten.

Playwrights API auf einer Rust-CDP-Engine: Chromium-Browser-Automation für Python und Node, ohne Treiber-Subprozess. (Alpha)

Was der Test ergab: Built from source with Rust 1.99 and Python 3.12; Chromium 155 installed and launchable; Python quickstart prints 'Rustwright works', 18-test CI subset passes, Node smoke and 19 Node tests pass, rustwright CLI (0.3.0) and native rustwright-cli (0.1.0) open/snapshot/close real browser sessions, MCP server answers... 68 Minuten.

Ein CLI-Tool zur Automatisierung Ihres alltäglichen Webbrowsers.

Was der Test ergab: Beachpatrol E2E suite passes all 14 tests with real headless Chromium browser, including smoke test (selenium.dev), error propagation, downloads, concurrent routing, duplicate detection, TypeScript commands, dependency resolution, --list, and --commands. 6 Minuten.

Web-Testing-Lösung für Nicht-Entwickler auf Basis von Puppeteer und Jest

Was der Test ergab: npm install, npm test (21 suites/261 tests all passing), npm run build, and Electron app launch on the virtual display all work; async test suite and unit tests verified with real jest runs. 15 Minuten.

Local-First-Open-Source-Fingerabdruck-Browser mit mehreren Profilen, basierend auf Chromium und Electron

Was der Test ergab: Project installs cleanly via npm ci, typechecks with tsc --noEmit, builds with electron-vite, all 126 unit tests pass, kernel lock checks pass, and Electron v43.2.0 launches and runs until terminated. 4 Minuten.

Open-Source-Webinfrastruktur für KI. Scrapen, crawlen und automatisieren Sie das Web, bereinigen Sie Markdown, Browser-Sitzungen, bereit für Ihre Agenten.

Was der Test ergab: Reader CLI builds, all 346 unit tests pass, the daemon starts with Playwright's bundled Chromium, and an end-to-end scrape of https://example.com via HTTP returns clean HTML and markdown content with a 200 status. 13 Minuten.

Verwandeln Sie jede Website in ein kompaktes CLI, das für KI-Agenten maßgeschneidert ist. Durchsuchen Sie das Web mit Hunderten von Tokens, nicht mit...

Was der Test ergab: only-cli v0.5.8 installs and runs on Node 20.11.1; 263 of 264 tests pass; the CLI fetches, distills, and renders public web pages with token-budgeted output and actionable numbered links. 3 Minuten.

Ein Paket, das als Wrapper um den headless mode vorhandener Webbrowser fungiert, um Bilder aus URLs und aus HTML+CSS-Strings oder -Dateien zu generieren.

Was der Test ergab: Package installed in venv, ChromiumHeadless defaults include --no-sandbox, 17 Chrome tests pass, CLI produces correct images, Edge tests gracefully skipped. 5 Minuten.

Die ADE für AI agents. Automatisieren Sie alles andere. Tun Sie Ihre wahre Arbeit.

Ein Schwarm von Einweg-Agenten für nicht zuschreibbare Web-Interaktion

Was der Test ergab: Ash Agents orchestrator server runs on port 8092 with ASH_DEMO_MOCK=1, all endpoints respond correctly, and all 12 unit tests pass. 6 Minuten.

Anti-Erkennungs-Browser-Server für KI-Agenten: REST API, die die Camoufox-Engine mit OpenClaw-Plugin-Unterstützung kapselt.

Was der Test ergab: Camofox Browser Server builds, starts on port 9998, creates browser contexts via Camoufox Firefox headless, navigates to https://example.com, returns accessibility snapshots, and passes the 677-test full suite with Node.js 20 and rebuilt native addons. 34 Minuten.

Agentenbasierte Browsersteuerung über Ihre eigenen Claude-/Cursor-Abonnements

Was der Test ergab: Bridge runs on Node 24, MCP endpoint responds with 14 browser tools, 175/175 tests pass, .endo-token file created with 0600 permissions. 3 Minuten.

Stoppen Sie AI agents davon ab, Dinge zu tun, die Sie nicht angefordert haben.

Was der Test ergab: npm install and tsc build succeed, all 50 test cases pass, CLI help responds with all commands listed. 17 Minuten.

Unofficial DSH (DeepSeek Harness) plugin: use chat.deepseek.com web models as an LLM provider - browser-login capture, PoW solving, SSE streaming...

Was der Test ergab: The project builds cleanly (tsdown produces lib/index.js and lib/client.js), all 62 offline test files pass, and the bundle product verification confirms all runtime features are present. 5 Minuten.

Ein vollständig freier agentischer Browser-Treiber für KI, wenige Tools, volle Kontrolle, echte Tarnung, höchste Token-Effizienz.

Was der Test ergab: Bladebro builds from source with zero clippy warnings, all 217 tests pass, Chrome for Testing launches under Xvfb, and the binary navigates real websites, reads page content, and queries cookies. 8 Minuten.

Ein lokal zuerst arbeitender, plattformübergreifender Electron-Desktop-Arbeitsbereich für Pi Coding Agent, mit Sitzungen, Projektdateien, Browser-Tools...

Was der Test ergab: Pi Agent Desktop v0.3.0 builds, all 1106 tests pass, and Electron smoke test verifies agent-host (pi=0.87.1) with all 12 function domains (renderer, RPC, session, worktree, git, watch, download, skills, channels, chat-appearance, toolchain) passing. 11 Minuten.

Hochleistungs-Web-Crawler-API, optimiert für LLMs. Verwandeln Sie jede Suche oder Website in sauberes Markdown mit Remote-Browsern. Firecrawl-Alternative.

Was der Test ergab: Teracrawl server starts on port 8085 with a local Chromium-backed mock Browser.cash pool and a mock SERP service. GET /health returns 200, POST /scrape converts a live URL to markdown via real headless Chromium, POST /serp/search returns mock search results, and POST /crawl combines both to scrape multiple URLs. 15 Minuten.

Lassen Sie Ihre KI-Agenten Ihr Chrome verwenden, während Sie darin angemeldet sind, in Hintergrund-Tabs. Von Alexey Indeev · Blog: read.aindeev.com · X...

Was der Test ergab: The Chrome Relay relay server starts, answers HTTP endpoints with correct status codes, and passes all 12 integration tests including agent WebSocket connections authenticated by secret and process markers, extension origin validation, web page rejection, and audit trail persistence. 20 Minuten.

OpenBrowser ist ein Framework für intelligente Browser-Automatisierung. Es kombiniert direkte CDP-Kommunikation mit einer CodeAgent-Architektur, bei der das...

Was der Test ergab: All 8030 unit and integration tests pass, CLI prints version and help, and headless Chromium via CDP navigates to about:blank and prints output correctly. 27 Minuten.

Local-first CLI für Agent Skills, Browser-Automatisierung, Wissensdatenbanken, externe CLIs und Terminal-AI-Chat.

Was der Test ergab: advai-cli 1.0.12 installed from source, all 78 unit tests pass, the CLI responds to all top-level commands, and the knowledge base subsystem creates, adds, searches, and syncs real local files. 1 Minute.

Local-First-CLI für Agent-Skills, Browser-Automation, Wissensbasen, externe CLIs und Terminal-AI-Chat.

Was der Test ergab: advai-cli 1.0.12 is installed in a venv, all 78 tests pass, and core commands (info, update, skill, kb, browser, cli) respond with valid output. 1 Minute.

Eine Webseite wie ein Programm ausführen

Was der Test ergab: webframe builds from source with patched glaze (preferGTK3=true), runs with WebKitGTK 4.1 from deb packages, executes JS pages, reports console output, supports exit codes and scripts. 19 Minuten.

codexqa: 11 lokale Agent Skills für Cursor, Claude Code, Codex & OpenClaw: Änderungsauswirkungsanalyse, AI-Code-Review, Defekt-Scan, Testfallgenerierung...

Was der Test ergab: The repo installs from a local checkout via npx skills with Playwright Chromium and the @openqa-cn/codexqa CLI in a user prefix; all repository checks pass: check-docs, compose-release-notes, checkout-boundary and inventory-service verifiers, polyglot fixture build, code-wiki 47/47, defect-analyzer full suite... 6 Minuten.

Ein Befehl für jede Schnittstelle: über APIs, Browser, Desktops, lokale Tools und MCP hinweg reale Software suchen, ausführen und inspizieren.

Was der Test ergab: Uni-CLI v1.2.1 builds from source, runs 3735 passing unit tests, and executes live commands (hackernews top, search, doctor) against real remote APIs on Node 22.23.4 (npm v10.9.9). The npm global package v1.3.0 is also installed and functional. 20 Minuten.

Open-Source-Plattform für selbst gehostete KI-Agenten für die KI-Teammitglieder Ihres Unternehmens. Bauen Sie Agenten auf Ihren eigenen Servern und Modellen...

Was der Test ergab: Backend Python environment (Python 3.15.2 via uv) installed, 254 packages resolved; frontend Node dependencies (771 packages) installed via bun; backend lint passes (ruff, formatting); 609 backend unit tests pass covering coverage gate, agent registry, labels, A2A client/server, mutation locks, observability, and... 15 Minuten.

Isolierte Linux-Desktop-Arbeitsbereiche für AI-Agenten, ein versteckter, dem Agenten gehörender Desktop und Browser über MCP, sodass ein Agent GUI- und...

Was der Test ergab: agent-workspace-linux 0.6.2 builds from source, all 199 tests pass, binary runs --help and --version, starts an X11 workspace with openbox and xdotool (extracted from apt debs), launches GUI apps (xlogo), takes screenshots via ffmpeg, and responds to MCP protocol initialization. 14 Minuten.

Indexieren Sie die undokumentierten APIs der Welt

Was der Test ergab: All 2434 unit tests pass after fixing 2 flaky async tests; pip editable install succeeds; CLI help commands work for bluebox-agent and bluebox-discover; core Python imports resolve without errors. 3 Minuten.

Puppeteer für Python, das für Anti-Bots unsichtbar ist, also keine Captchas: gleiche API, Anti-Erkennungs-Stealth-Headless-Firefox, unerkannter Fingerabdruck...

Was der Test ergab: Editable install resolved all dependencies, default pytest suite passes (219/259), CLI version and fetch commands work, and the browser engine was downloaded and cached. 3 Minuten.

Open-source, selbst gehostete Alternative zu OpenAI Dots, Grok Bot. Entwickelt, um von Anti-Bot-Systemen nicht erkennbar zu sein.

Was der Test ergab: npm ci installed 428 packages, the CLI bundle and web client built, npm run typecheck passed, npx vitest run gave 2103 passed/3 skipped and go test gave 120 passed after I fixed the secret-input backspace bug and the execEnv DISPLAY bug, and the control plane served HTTP 200 on /api/health, /api/dots and the web UI... 22 Minuten.

Stealth-Headless-Browser für KI-Agenten, umgeht Cloudflare, Bot-Erkennung und Anti-Scraping. Direkter Ersatz für Puppeteer/Playwright.

Was der Test ergab: Camofox browser server installed and verified: Node 22.23.4 in user space, Camoufox 1.3GB binary downloaded, GeoIP 50MB database downloaded, server starts at localhost:9377 with Xvfb virtual display, creates browser tabs navigating to real URLs, returns accessibility snapshots with element refs, and closes cleanly on... 13 Minuten.

Open-Source, selbst gehostete Alternative zu OpenAI Dots, Grok Bot. Entwickelt, um von Anti-Bot-Systemen nicht erkannt zu werden.

Was der Test ergab: dots installs, its 4 tests pass, and the UI server runs and drives its bundled browser with a real model call, navigating https://example.com and reporting HTTP 200. 7 Minuten.

JavaScript-Agent für In-Page-GUI. Steuern Sie Webschnittstellen mit natürlicher Sprache.

Was der Test ergab: Install, sequential build, typecheck, lint, and all 69 unit tests pass. The project is fully functional with Node v22. via nvm. 27 Minuten.

Hochleistungs-Browser-Automatisierungsbrücke und Multi-Instanz-Orchestrator mit fortschrittlicher Stealth-Injektion und Echtzeit-Dashboard.

Was der Test ergab: A source-built PinchTab server (binary reports pinchtab dev) is running on 127.0.0.1:9867 with a responsive always-on headless instance and answered authenticated health, navigate, snapshot, text, title, and screenshot API calls with HTTP 200, while the full Go unit suite (9166 passed, 18 skipped) and scripts/check.sh... 19 Minuten.

Grasp hilft Ihnen, mehrere Projekte und parallele Coding-Agenten in einem visuellen Workflow zu verwalten, damit Menschen schneller verstehen und mehr...

Was der Test ergab: With user-local Go 1.27.3 and Node 24.12.0, the built Grasp server and gateway binaries start and answer health 200, admin login and project APIs return 200 with seeded data, and the server, web, docs, gateway, and sandbox build, test, and coverage suites all pass. 18 Minuten.

🗃 Open source self-hosted web archiving. Takes URLs/browser history/bookmarks/Pocket/Pinboard/etc. saves HTML, JS, PDFs, media, and more...

Was der Test ergab: ArchiveBox 0.9.65rc24 installed in a Python 3.13 venv; data directory initialized with SQLite; Django admin server starts and serves HTTP on port 5797; 125 tests pass; full archiving (add, crawl) requires wget/chrome/yt-dlp which are not installed in this container without root. 12 Minuten.

Open-Source-AI-Agent für Web-Automatisierung. Verwenden Sie Ihren echten, angemeldeten Browser, um alltägliche Aufgaben zu automatisieren.

Was der Test ergab: Dependencies installed, project builds to dist/ (background.iife.js 1,848.81 kB, manifest.json), TypeScript type-check passes across all 15 packages, unit tests pass (14/14). 15 Minuten.

Führen Sie AI Agent in Ihrem browser aus.

Was der Test ergab: The Browser Use WebUI serves HTTP 200 on port 7788 with the full Gradio UI, runs an agent against the local mock, and completes tasks with a decodable recording GIF and agent-history JSON. 37 Minuten.

Desktop-Automation-MCP-Server: Computer Use für jeden AI-Agenten, Steuerung von Bildschirm, Fenstern, Maus/Tastatur und Chrome über das Model Context Protocol...

Was der Test ergab: nuphus-mcp v0.3.3 installs via npm, initializes over stdio JSON-RPC responding to initialize/tools/list/tools/call, returns screen size (1280x800), and captures valid PNG screenshots in headless Xvfb. 12 Minuten.

Für EHRs, Zahlungsportale und jede App, durch die Ihr Team klickt. Eine Person oder ein Agent zeigt die Aufgabe; OpenAdapt wandelt sie in ein lokales Programm...

Was der Test ergab: Package installs and all 288 tests pass; CLI, doctor, version commands work; recording generates valid artifacts; compile is CPU-bound by onnxruntime in this container but eventually produces bundles. 20 Minuten.

Diese Layout-Engine kann die schwierigsten Layout-Probleme lösen, die man sich vorstellen kann. Ihre Ausgabe ist DTP-tauglich und deterministisch. Sie ist...

Was der Test ergab: vmprint CLI and engine ran in this container on Node 18 despite EBADENGINE install warnings: npm test exited 0 (engine 77+77 fixtures, packaged-integration 1 page/1107 bytes), the CLI rendered valid text-bearing PDFs with bundled local fonts and version 0.1.0, and engine.layout() produced 1 page x 1 box containing... 18 Minuten.

Open-source Python-Bibliothek für AI browser agents, plus Browser Use Cloud: Stealth-Browser und eine gehostete agent API.

Was der Test ergab: browser-use v0.13.10 installed in a Python 3.12 venv with uv, Chromium headless installed via playwright, and all 563 CI tests pass (529 passed, 34 skipped) after fixing 2 test identity comparison bugs in test_beta_agent.py that only manifest under xdist worker parallelism. 75 Minuten.

Machen Sie jede Website zu einer CLI & nutzen Sie Ihren eingeloggten Browser durch den AI-Agenten.

Was der Test ergab: OpenCLI 1.8.8 builds and runs on Node 22.14.0; 632 test files pass (7325 tests, 3 skipped) across unit, extension, adapter, smoke projects; CLI binary answers version 1.8.8 and lists 1366 registered commands. 27 Minuten.

Terminal-UI, um Dinge im Browser zu erledigen

Was der Test ergab: The Rust workspace builds cleanly, all 2058 Rust and 28 Python tests pass, cargo fmt is clean, and both the CLI (browser-use-terminal 0.1.8) and TUI (but 0.1.8) binaries run, with the TUI rendering its setup screen and responding to real keyboard input in a PTY session. 40 Minuten.

Der schnellste browser für AI agents, um browser-Automatisierung auszuführen, entwickelt, um Ihren angemeldeten browser-Zustand mit Ihren AI agents zu teilen...

Was der Test ergab: 494 unit tests pass on Node 22.23.4 with mocking (FakeEgo test double), the build produces a CLI binary that prints help text, and type checking passes cleanly. Real browser e2e was not attempted because no ego lite runtime is available in this container. 2 Minuten.

Sich selbst weiterentwickelnder Agent: baut einen Skill-Baum aus einem 3.3K-Zeilen-Startcode auf und erreicht damit vollständige Systemkontrolle mit 6x weniger...

Was der Test ergab: After a venv install of the declared UI and test dependencies, 275 tests pass, the TUI starts, the Streamlit UI completes a mocked tool-using turn with MOCK_FINAL: 246810, and launch.pyw opens a live 1200x900 GenericAgent window on DISPLAY=:99 using PyQt6 and an extracted libxcb-cursor. 29 Minuten.

Verwandeln Sie jede Webseite mithilfe von LLMs in strukturierte Daten.

Was der Test ergab: The project installs and builds without errors; 8/8 test cases pass with a mocked OpenAI Responses API endpoint. 24 Minuten.

AI-Agent-first JS-Reverse-Engineering-MCP-Server: Chrome-Debugging mit grafischer Oberfläche, Haltepunkte, Netzwerk-/WebSocket-Analyse...

Was der Test ergab: The js-reverse-mcp v4.0.5 TypeScript project compiles to JavaScript, its full test suite of 114 tests passes, and the MCP server binary responds to JSON-RPC initialize on stdin/stdout. A Node.js v22.12.0 upgrade was applied (portable) and the cloakbrowser optional dependency was installed. Google Chrome is not... 4 Minuten.

Ein leistungsstarker MCP-Server (Model Context Protocol), der eine Komplettlösung für den öffentlichen Webzugriff bietet.

Was der Test ergab: The Bright Data MCP server installs and all 21 unit tests pass under Node.js v22.12.0; the server starts listening when API_TOKEN is set. 4 Minuten.

Codex computer use, entkoppelt von der App, zur Verwendung in jedem Harness.

Was der Test ergab: LCU 0.9.1 installed and verified extracting the official ChatGPT 26.915.31945 (CUA 0.0.16) app fixture, Python 435-test suite passes, adapter tests 88/103 pass, and lcu doctor confirms window listing and screenshot on virtual display. 7 Minuten.

Lassen Sie Ihren AI-Agenten die Quellen hinter Anmeldungen und Bezahlschranken abrufen.

Was der Test ergab: Actionbook monorepo builds and all test suites pass (js-sdk 78/78, mcp 45/45, tools-ai-sdk 7/7, openclaw-plugin 39/39, cli 482/483), MCP server starts on stdio listing 5 tools, Rust CLI reports version 1.6.0, and json-ui renders reports, with the only gap being lsof not in the container and the remote API returning a... 13 Minuten.

Selbst gehostete Websuche für AI agents und SEO. Google, Bing, Yandex, Baidu, DuckDuckGo & Ecosia, in einem echten Browser gerendert: sortierte Ergebnisse und...

Was der Test ergab: OpenSERP v0.8.13 builds, all 12 unit test suites pass, and the HTTP server starts, serving /health and /ready endpoints on 127.0.0.1:7000. 8 Minuten.

Playwright-Integration für Scrapy

Was der Test ergab: scrapy-playwright 0.0.48 installed and builds; chromium handler works end-to-end (73 tests pass); firefox works standalone but 3 firefox test classes hang in pytest-twisted; webkit tests correctly skip on Linux; missing `file` system command patched in test. 61 Minuten.

WebAI2API: Web-KI zu OpenAI-API über Camoufox. Unterstützt LMArena/Gemini und mehr, Multi-Window-Parallelität & Kontoisolierung.

Was der Test ergab: The WebAI2API server starts on port 3000 with a Camoufox browser instance, serving OpenAI-compatible /v1/models, WebUI, and /v1/cookies endpoints, all returning HTTP 200, though chat completions require real AI website credentials via the browser adapter and cannot produce output without logging in. 7 Minuten.

Gemini Nexus ist eine KI-Assistent-Erweiterung für Browserszenarien. Sie integriert Gemini Web, Gemini API und OpenAI-kompatible Schnittstellen und unterstützt...

Was der Test ergab: Gemini Nexus installs and builds successfully on Node 18 after downgrading jsdom to 26.x and knip to 5.x; all 1437 tests across 201 test files pass via npm run check; npm run package:extension produces a valid artifacts/chrome-extension directory; the Vite dev server serves the sidepanel, sandbox, and settings... 13 Minuten.

Geben Sie Ihrem AI-Agenten einen echten Browser: mit einem Menschen in der Schleife. Open-Source-MCP-nativer Browser-Agent.

Was der Test ergab: Controller and client packages install in a venv; 1189 test suite tests pass via FastAPI TestClient with mocked browser node; Docker-based compose stack not available so full end-to-end with Playwright cannot run. 6 Minuten.

Gemini-Zeichnen-MCP und Skill über den Browser, kann in OpenClaw oder jedem Agent verwendet werden, der MCP unterstützt. Gemini-Zeichnen-MCP und Skill...

Was der Test ergab: Dependencies install cleanly, the MCP server starts and enumerates all 21 tools, the Atlas OpenAI-compatible provider works end-to-end against a local mock server, and the daemon starts with /health returning HTTP 200; the Gemini browser-driven tools could not be exercised because no Chrome/Chromium binary exists in... 9 Minuten.

Die CLI für AI-Agents zur Steuerung von Chrome. Keine Konfiguration, agent-agnostisch, kampferprobt.

Was der Test ergab: Surf v2.20.0 builds and all 81 test files pass (1177/1179 tests) using Node.js v22.12.0. The two test files that failed with SyntaxError were fixed by converting import-destructure patterns from require() to ESM import syntax. 19 Minuten.

Verwenden Sie agent-browser-cli für Browser-Wahrnehmung und -Steuerung. Geeignet für Tab-Scanning/-Wechsel, JS-Ausführung auf Seiten, Cookies, CDP...

Was der Test ergab: Daemon runs on default ports with config matched; with the mock extension connected, status/doctor/tabs/tabtree/scan/exec/open/close/lookup/profile-label/network/console/screenshot/save-pdf/install-skill all return ok:true and doctor reports all checks ok, while click/fill/send-keys on @e refs and mouse-click remain... 35 Minuten.

Lokaler Sprachassistent auf Französisch: Claude oder Ollama (offline), Hue-Hausautomation, OBS, Kalender, Browser, Twilio-Anrufe, MCP-Server. Python.

Was der Test ergab: Jarvis installs cleanly, its 181-test suite passes (4 Windows-only cases skipped), the Signal Matin pipeline emits valid A4 PDFs in all three density modes without overflow, and the OpenAI provider answers through a schema-correct local mock; only a physical microphone is missing. 36 Minuten.

Ein Skill für AI agents: Durchsuchen Sie das Web mit SearXNG, browsen Sie mit Camofox, umgehen Sie Schutzmaßnahmen mit CloakBrowser. Anti-Halluzination von...

Was der Test ergab: npm install succeeds, CloakBrowser (with Node 20, not the system Node 18) fetches live pages, the SearXNG and Camofox deterministic scripts pass their full command flows against schema-correct mocks, unit suites pass 28/28 and 12/12, and setup.sh/audit.sh complete without failed checks; real SearXNG/Camofox Docker... 33 Minuten.

Der KI-Agent hat gemeldet, dass der Vorgang abgeschlossen sei. Flyto2 legt den Nachweis vor.

Was der Test ergab: The Python package installs, builds, and 4751 unit/module/contract tests pass. The CLI responds to help. Documentation and brand checks pass. The container lacks system ping and a newer Node for jsdom@29, both worked around. 54 Minuten.

Browser Use Box: ein 24/7 Claude Code Agent für Playwright-style Browser-Automation mit Browser Use Cloud, Telegram und einem echten Browser auf jeder Box, die...

Was der Test ergab: Python venv at /tmp/bux-venv with websockets, httpx, Pillow installed. All 84 agent tests pass (telegram_bot: 63, mini_app: 16, bux_miniapp_tunnel: 3, login_flow: 2). The project can't fully launch without BROWSER_USE_API_KEY, TG_BOT_TOKEN, and systemd, those are real third-party services, but the full test suite... 4 Minuten.

Plattformneutrales Browser Use für AI-Agenten: echte Chrome-Automatisierung mit CLI + SDKs, ohne Lock-in, denkbar einfach.

Was der Test ergab: The repo installs and builds in this container; the Go CLI/MCP/SDKs run and answer requests through a standing mock of the Chrome extension, and every test suite in the repo passes after the crypto fix. 13 Minuten.

Rendern Sie eine echte Chromium-Ansicht in einem Herdr-Pane und steuern Sie diese über CDP.

Was der Test ergab: Project builds, typechecks clean, all 140 tests pass, CLI help displays, and test HTTP server starts on localhost. 33 Minuten.

Verwandeln Sie Ihr ChatGPT- oder Claude-Konto in eine voll funktionsfähige OpenAI-kompatible API. Es werden keine API-Schlüssel benötigt. Unterstützt...

Was der Test ergab: CatGPT Gateway starts with PROVIDER=minimax, passes all 7 MiniMax provider tests, serves health/endpoints/models/chat completions on port 8000, and responds correctly to OpenAI SDK and curl requests. 6 Minuten.

KI-gestützte Login-Automatisierung. Verwendet Claude zur Klassifizierung von Login-Seiten und Playwright zur Interaktion mit ihnen.

Was der Test ergab: The Next.js app builds, launches, returns HTTP 200 on / and /api/chat, and responds to all API actions (start, submit, close, error handling) using local Playwright Chromium with a mock heuristic page classifier. 17 Minuten.

Agent-Skill zum Reverse Engineering eines SaaS-Produkts über den Browser in eine Wissensbasis für den Neuaufbau: Screens, Regeln, Datenmodell, Design-Tokens...

Was der Test ergab: All 32 automated tests pass under Node.js v22.14.0 and Playwright Chromium headless; all 4 CLI scripts exit 0 with correct usage and the end-to-end workflow (init, check, build-report, pack) produces valid output. 8 Minuten.

pi-Erweiterung, die agent-browser als natives Tool für Browser-Automatisierung bereitstellt.

Was der Test ergab: npm install, build, and doctor pass; 1137 of 1256 tests pass with fake-agent-browser fixtures; 79 pre-existing cold-reopen and daemon-boundary failures remain. 84 Minuten.

Ein MCP-Dienst, der es Agenten ermöglicht, direkt echtes Chrome zu steuern, unterstützt vier Funktionen: Seiten-Scanning, CDP, Screenshots und physische...

Was der Test ergab: In a fresh .venv the project installs and builds, its CLI prints help/extension path/hermes config/doctor JSON, its MCP stdio server responds to initialize and tools/list with 19 tools, and against a mock Chrome bridge list_tabs, execute_js, scan_page, page screenshot, and desktop screenshot all returned real results... 28 Minuten.

Verwandeln Sie Ihren Computer in eine AI-Agent-Workstation, die Sie von Ihrem Telefon aus steuern können.

Was der Test ergab: Opensteer 0.11.2 is installed as a uv global tool, all 100 unit tests pass, the CLI responds to --version (0.11.2), --help, and -c execution, and skills are installed. 1 Minute.

DeepSeek Harness plugin: geben Sie Ihrem Agenten einen Browser mit einer persistenten Identität: Fingerabdruck-Spoofing auf Engine-Ebene, unbegrenzte...

Was der Test ergab: The dsh-antibrow plugin package installs and packs cleanly; the smoke test passes with a mock MCP server implementing all 16 AntiBrow browser automation tools, verifying that the harness plugin bridge correctly discovers and routes all tools as mcp__antibrow__* entries. 11 Minuten.

AI coding workstation: Claude Code + web UI + 8 AI CLIs + headless browser + 50+ tools

Was der Test ergab: All 285 Node.js unit tests, 5 Python notification tests, and the CLI persistence shell test pass. Repository structure is validated end to end with product facts contracts, security policy, documentation, and patch scripts all verified. 2 Minuten.

Ein MCP-Dienst, der Agenten die direkte Steuerung von echtem Chrome ermöglicht und Seiten-Scan, CDP, Screenshots sowie physische Eingabe unterstützt.

Was der Test ergab: agent-browser-mcp CLI and MCP server install, start, and respond to all 20 tools; desktop automation tools work against the Xvfb display; browser CDP tools await a Chrome extension connection. 6 Minuten.

Eko (Eko Keeps Operating) - Erstellen Sie einen produktionsreifen agentischen Workflow mit natürlicher Sprache - eko.fellou.ai

Was der Test ergab: All 4 packages build successfully. 12 of 14 test suites pass (14 of 16 individual tests) in eko-core with a mock LLM server. Remaining failures: test/llm/utils.test.ts has a pre-existing unhandled rejection for an intentional timeout scenario; test/llm/mcp.test.ts requires an external MCP SSE server on localhost:8083... 27 Minuten.

macOS-App für 24/7 AI-Agenten in einer IDE mit Speicher, geplanten Aufgaben, Browsernutzung + Zugriff auf Whatsapp, Telegram, Slack.

Was der Test ergab: The dorabot backend compiles from source, its WebSocket gateway serves HTTP health at 200 on a Unix socket and handles RPC methods for auth, sessions, skills, agents, calendar RRULE scheduling, goals CRUD, projects/tasks, and provider detection against a real SQLite (WAL) database; the interactive CLI lists skills and... 29 Minuten.

Open-Source-Benchmark für Browser-AI-Agenten für tägliche Aufgaben.

Was der Test ergab: Python package clawbench-eval v0.10.0 installs and builds; all CLIs (clawbench, clawbench-run, clawbench-batch, clawbench-rescore, clawbench-analyze, clawbench-reproduce, clawbench-harbor-adapt, clawbench-edgebench-adapt, clawbench-edgebench-judge, clawbench-prorl-submit, clawbench-prorl-mock) are importable and... 3 Minuten.

Your AI friend right in your browser

Was der Test ergab: npm install completed 771 packages with warnings about node version requirements; npm run build produces dist/ with manifest.json, background.js, sidepanel/panel.{js,css,html}, and content scripts; npm test passes 233 checks; integration tests pass 19; orchestrator harness passes 7; tsc typechecks without errors... 12 Minuten.

Leistungsstarker CAPTCHA Solver (Turnstile, cf_clearance, reCAPTCHA v3, AWS WAF) entwickelt mit FastAPI + Camoufox. Hohe Erfolgsquote, Proxy-Unterstützung und...

Was der Test ergab: The FastAPI server runs on 0.0.0.0:8000, registers all 5 endpoints (/turnstile, /clearance, /aws-token, /recaptchaV3 GET+POST, /result), initializes a browser pool via camoufox, and correctly accepts task submissions and returns pollable results. 4 Minuten.

Open-Source-AI-Kollegen, die jeweils einen eigenen Computer bekommen: einen Browser, Dateien und Tools, wobei jede Aktion vorher entschieden und danach...

Was der Test ergab: bun install and all 3985 non-integration unit tests pass. The 69 failures are all infrastructure-gated (no PostgreSQL for integration tests, no Docker for compose tests, 2 pre-existing Mastra .env leakage failures). 49 Minuten.

Ein Agenten-Browser-Harness: eine KI-Seitenleiste und eine Kugel in Ihrem eigenen angemeldeten Chrome, Edge, Arc, Brave oder sogar Firefox, ausgeführt von dem...

Was der Test ergab: konnte nicht verifiziert werden; das Log zeigt, wo es stehen blieb. 8 Minuten.