惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

J
Java Code Geeks
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
有赞技术团队
有赞技术团队
博客园 - 【当耐特】
云风的 BLOG
云风的 BLOG
Martin Fowler
Martin Fowler
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
量子位
Engineering at Meta
Engineering at Meta
博客园 - 叶小钗
T
The Blog of Author Tim Ferriss
Recent Announcements
Recent Announcements
罗磊的独立博客
B
Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
U
Unit 42
Microsoft Azure Blog
Microsoft Azure Blog
D
Docker
N
Netflix TechBlog - Medium
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
B
Blog RSS Feed
I
InfoQ
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
V
V2EX

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
rabbitholes: inline explanations with no server in the mi...
J Now · 2026-06-11 · via DEV Community

J Now

Most browser extensions that call an external API route your data through their own server. That's how they log usage, build analytics, gate features behind subscriptions, and eventually get acquired or shut down. I didn't want that architecture for rabbitholes.

rabbitholes is a Chrome extension that renders inline explanations for any text you highlight. The privacy design is simple: your browser talks directly to api.anthropic.com and api.search.brave.com. No intermediary server exists. There's nothing to breach, no company database holding your query history, no subscription to cancel when the startup pivots.

The technical consequence of that choice is that you supply your own Anthropic API key. It's stored in chrome.storage.sync, which Chrome encrypts and ties to your Google account — it never leaves the browser. The extension is Manifest V3, so the service worker model means there's no persistent background process phoning home.

What the extension actually does: highlight any text on any page, and a shadow-DOM tooltip appears next to your cursor with an explanation from Claude Haiku 4.5. Shadow DOM so nothing bleeds into the host page's styles or layout. Click any word in the explanation to go deeper. Drag across a phrase to explore that instead. Every answer surfaces two suggested rabbit-hole topics — the most interesting threads from that explanation — one click away. A counter tracks how many hops deep you've gone.

The Globe icon re-runs the query enriched with Brave Search results, with source chips you can click through. The Pencil icon opens a follow-up input that inherits your current context. Neither of those interactions routes through anything I control.

Zero analytics. Zero telemetry. I have no idea how many people use this or what they look up, which is the point.

https://github.com/robertnowell/rabbitholes