Kapture MCP Browser Automation

Raycast Companion

A browser extension to give more context to Raycast Interact with the web in a new way by leveraging Raycast AI to summarize websites or videos, analyze content, and automate tasks in your browser. The extension gives Raycast a better understanding of what you are looking at in your browser. Create custom AI Commands with the {browser-tab} dynamic placeholder in Raycast. Explores commands on https://ray.so/prompts. Features you'll love: 🤏 Summarize the focused tab with the built-in "Summarize Website" command 🔤 Create custom commands that use AI to interpret the focused tab 🔁 Get inspired by our community (https://raycast.com/community) and share your commands Note: The extension requires Raycast to be installed.

Nanobrowser: AI Web Agent & Automation

Automate web tasks with AI! NanoBrowser is an open-source Chrome extension that lets you extract data, fill forms, and more. An open-source and local-first web automation agent that runs in your browser. 1️⃣ 100% Free: No subscription fees or hidden costs. Just install and use your own API keys 2️⃣ Privacy-Focused: Agent runs in your local browser instead of cloud 3️⃣ Flexible LLM Options: Supports SOTA LLM models as well as local models 4️⃣ Fully Open Source: Complete transparency in how your browser is automated ✅ Multi-agent System: Specialized agents collaborate to accomplish complex web tasks. ✅ Interactive Side Panel: Intuitive chat interface with real-time status updates. ✅ Task Automation: Seamlessly automate repetitive tasks across websites. ✅ Follow-up Questions: Ask contextual follow-up questions about completed tasks. ✅ Conversation History: Easily access and manage your interaction history. ✅ Multiple LLM Support: Connect your preferred LLM providers and assign different models to different agents. ⚠️ While Nanobrowser may work on some Chromium-based browsers, they are not officially tested and supported. 1️⃣ Click the Nanobrowser icon in your toolbar to open the sidebar. 2️⃣ Click the Settings icon (top right). 3️⃣ Add your preferred LLM API keys. 4️⃣ Choose which model to use for different agents (Navigator, Planner, Validator). 5️⃣ Send your commands to Nanobrowser 1️⃣ Go to TechCrunch and extract top 10 headlines from the last 24 hours 2️⃣ Look for the trending Python repositories on GitHub with most stars 3️⃣ Find a portable Bluetooth speaker on Amazon with a water-resistant design, under $50. It should have a minimum battery life of 10 hours We are open source. We need your help to make Nanobrowser even better! Contributions of all kinds are welcome: 1️⃣ Share prompts & use cases in our Discord server 2️⃣ Create issues or even submit pull requests on our Github repository ❤️ Loving Nanobrowser? Leave us a review on the Chrome Web Store and help others discover this powerful extension! Your support means everything to us.

Retriever: AI Web Agent

Turn your browser into a self-driving AI Agent. Automate scraping, form filling and monitoring with simple prompting. Tired of endless clicking, copying, and pasting? Transform your browser into an intelligent, self-driving powerhouse. Meet Retriever, the advanced AI agent that lives in your browser. From simple data extraction to complex, multi-step workflows across dozens of tabs, we turn natural language commands into automated actions. 🔑 Get Started for FREE: Bring Your Own Model/Key — Zero Extra Cost Already paying for ChatGPT Plus or Claude Pro? Use your existing subscription to power Retriever. • OpenAI & Anthropic OAuth: Sign in with your ChatGPT or Claude account and use FREE. • Bring Your Own API Key: Drop in your OpenRouter, Kimi, or Gemini key and you're off. • Can even setup and run with locally hosted model ✨ Unleash Unprecedented Capabilities • 🛠️ NEW: AI Subroutines: Teach Retriever a workflow once, and we'll intercept the underlying API calls and turn them into a deterministic, zero-token tool. Send an Instagram DM, post on X, fire a LinkedIn connection request — reusable across every future run with full web context. Global subroutines are shared across the community. • 🎙️ NEW: Voice Input: Hit the mic and dictate prompts or recordings. Powered by on-device Chrome transcription. • 📋 NEW: Accessibility Tree Clipping: MacCtrl+C copies the full Agent Accessibility Tree of the active tab — far richer than plain text grabbers. Paste into your own knowledge base, Obsidian, or any LLM chat. • 📚 Knowledge Base (RAG) & Memory: Don't just browse — remember. Index any open tab, or scrape + index URLs directly from the cloud dashboard, powered by Gemini File Search. 📱 NEW: Control Retriever from WhatsApp Your browser agent, now one text message away. • Trigger workflows on the go: Message /schedule check competitor pricing daily or /trigger new Product Hunt launches right from WhatsApp. • Check results anywhere: /check_schedule_results summarizes results while your on the go. • Run shortcuts remotely: Save a task as shortcut and rerun from WhatsApp as a slash command. ⚡ Scheduled Monitoring & "While You Sleep" Automation Turn Retriever into a 24/7 monitoring machine. Schedule ANY workflow to run automatically — hourly, daily, or on a custom cron. • Set it and forget it: Track prices, inventory, competitor news, or social metrics without lifting a finger. • Auto-Sync to Sheets: Automatically append results to Google Sheets with timestamps for an instant live dashboard. • Bypass Blocks: Because Retriever uses your active browser session, it accesses protected data behind logins that other bots can't reach. • Manage everything at rtrvr.ai/cloud: See every execution, recording, schedule, and knowledge base in one dashboard — with one-click "re-run via API" snippets on every task. Chat with your docs: Cited answers from your indexed research. Agent context: Let the agent reference your KB mid-workflow for smarter decisions. New MCP endpoints: List stores, query, and index directly from ChatGPT/Claude/Cursor. Learn more: https://www.rtrvr.ai/docs/knowledge-base 💻 CLI & SDK Integration (Developer Mode) Control your local browser extension directly from your terminal. • One CLI, three modes: npm install -g @rtrvr-ai/cli, then rtrvr run or rtrvr scrape. • Smart routing: Automatically route tasks between our Cloud infrastructure and your Local Extension. • Authenticated automation: Run scripts that execute inside your logged-in browser session. 🌐 Give ANY AI Chat Browser Superpowers (MCP) Copy your unique rtrvr.ai MCP endpoint into ChatGPT, Claude, Cursor, or your own code. Instantly give them the power to control your browser, extract live data, query knowledge bases, list your tools & recordings, and perform complex automations. No local installation required. 🎓 Teach rtrvr.ai a "Trick" (No-Code) Don't write code — just show us! Perform the task once (clicks, typing, navigation) and rtrvr records your actions, including the underlying network calls. Save it as a "Trick" and trigger it anytime from the extension, WhatsApp, MCP, or CLI. 📊 Powerful Data Extraction & Crawling Scrape thousands of rows from any website, even with infinite scroll. Our DOM-based approach ensures precision where vision-based agents fail. Export to Google Sheets or structured JSON instantly. ☁️ Cloud Control & Remote Execution Design workflows in the dashboard and trigger them to run on your extension remotely. Start a complex research task from your phone, WhatsApp, or an API call. 🔒 Coming Soon: Private Mode Zero data residency on $99/mo and above tiers — no logs, nothing stored, everything in memory. Built to meet compliance obligations. Reach out for verification or custom requirements. 🎯 Who is rtrvr.ai for? 📈 Marketers & Sales: Automate lead gen, social posting, CRM entry. 🛍️ E-commerce Owners: Monitor competitor pricing and inventory 24/7. 🔬 Researchers: Index journals into your Knowledge Base in minutes. 🧑‍💻 Developers: Use the CLI/SDK/MCP to integrate browser automation anywhere. 🙋 You: Automate daily life, from booking flights to organizing expenses. Bring Your Own Everything: Your ChatGPT/Claude subscription, your API keys, your browser session. Universal Connector: Plug your browser into ChatGPT, Claude, Gemini, and WhatsApp. Secure by Design: Operates within your browser using your existing logins — no password handover. DOM-Powered Precision: Higher accuracy than vision-only agents. Constantly Evolving: New features shipped every week. Stop wasting time on manual web tasks. Install rtrvr.ai today and give your browser a brain.

AnythingLLM Browser Companion

Bring AnythingLLM directly into your browser to curate and collect content on the web directly into your AnythingLLM workspaces. **This extension requires you to have AnythingLLM** The AnythingLLM browser companion allows you to seamlessly send and collect information you find in your browser and import or send that data directly into your AnythingLLM workspaces! Works for both online instances as well as desktop clients >=v1.6.5 The browser companion supports white-labeling as well as customization via our Open-source repo: Browser: https://github.com/Mintplex-Labs/anythingllm-extension AnythingLLM: https://github.com/Mintplex-Labs/anything-llm AnythingLLM Desktop: https://anythingllm.com/download