Conduit — The AI Data Bridge

Structured browser data for AI agents. All data stays local on your machine with zero cloud dependencies.

Conduit organizes the massive streams of data flowing through your browser into structured, actionable insights — serving them instantly to your AI agents, automation scripts, and local tools. Whether you're cataloging online purchases natively with our Amazon integrator, automating complex browsing tasks programmatically, or giving LLMs direct visibility into your live browsing window — Conduit turns your browser into a personal, sovereign data engine. 🔥 KEY FEATURES 📡 Smart Data Capture Conduit automatically intercepts and structures data from supported platforms (Amazon, Walmart) into clean, organized formats — all processed locally. Query captured data via REST API, export to CSV or JSON, and filter by platform or time range. 🤖 MCP Server — Native AI Agent Integration Conduit inherently speaks MCP (the Model Context Protocol). Give Claude Desktop, Cursor, Windsurf, or your own scripts absolute real-time awareness of what your browser sees: • "What did I buy on Amazon last month?" • "Summarize the articles in my open tabs" • "Read these page elements and execute actions" 20 purpose-built MCP tools expose everything: tab control, page reading, screenshots, DOM interaction, cookies, bookmarks, browser history, and more. ⚡ Full Local REST API Every capability is accessible via clean REST endpoints on localhost:7777: • GET /data — query captured event streams • GET /tabs — list open browser tabs • POST /action — click, type, scroll, and interact with pages • POST /screenshot — capture visual snapshots • GET /browser-history — search native browser history • GET /history — query the persistent event data lake 🛒 The Amazon Engine Initiate a 1-click import of your complete Amazon order history — years of purchase data cataloged with product details, pricing, and dates. Primed for analysis, expense tracking, or integration with your AI workflows. 🔧 Recipes — Toggleable Data Connectors Enable or disable structured data extraction per-platform via simple toggle switches. Each recipe intercepts platform-specific API traffic and transforms it into clean, queryable data. 🔐 YOUR DATA STAYS WITH YOU Zero cloud. Zero telemetry. The extension communicates exclusively with a local Node.js host server on 127.0.0.1. Nothing leaves your machine. You own your data completely. 📦 EDITIONS & TIERS All users activate a comprehensive 14-day Pro Trial on first install — full access to every REST endpoint, automation tool, and MCP bridge. After trial: core data capture, history, and read-only MCP tools remain free. Pro unlocks autonomous actions, tab control, cookies, and the WebSocket firehose. 🏗️ ARCHITECTURE • Extension: Lightweight MV3 service worker — passive data interception + recipe-driven extraction • Host: Local Node.js server — REST API (:7777), WebSocket stream (:7778), MCP Streamable HTTP (:7779) • Storage: Append-only JSONL data lake — persistent, portable, zero-dependency Designed by Sophia Labs. https://sophialabs.gantlett.io/conduit