Search Page - Moozonian Search

github.com• Mar 1, 2026• 1 min read

Show HN: Epstein-Search – Local, AI-Powered Search Engine for the Epstein FilesHi HN, I built epstein-search, an open-source Python CLI and library to run semantic search and RAG over the publicly released Epstein Files (unsealed court documents, depositions, FBI reports, and flight logs). I wanted a way to easily navigate through these thousands of pages of unstructured legal PDFs without relying on a paid third-party service or sending data back and forth to a cloud provider. How it works under the hood: Running epstein-search setup downloads ~100K pre-computed document chunks and embeddings (using all-MiniLM-L6-v2) based on the public 20K document corpus. It imports these into zvec (a local vector database) so the index is ready in about a minute. Standard search (epstein-search search) embeds your query locally using sentence-transformers and does a vector similarity search. This step is 100% offline and requires no API keys. For the conversational RAG mode (epstein-search chat or ask), it uses LiteLLM. You can point it to an Ollama or LM Studio instance for

levaevro.com• Feb 27, 2026• 1 min read

Show HN: BGN/EUR converter for Bulgaria's euro adoptionBuilt this as a side project ahead of Bulgaria joining the eurozone (Jan 1, 2026).A few things I tried that seemed to work:- Launched ~2 months before the fixed rate announcement so Google had time to index - The domain "levaevro.com" is a transliteration of "лева в евро" (leva in euro) – exact-match domains still work surprisingly well in smaller language markets - Instead of canonicalizing all query param URLs to the homepage, I submitted 52 parameterized URLs to a custom sitemap (?amount=100&from=BGN, ?amount=500&from=BGN, etc.) – each one targets a specific search query like "100 лева в евро". Zero extra dev work, same template. - Added a llms-sitemap.xml for AI crawlers (ChatGPT, Perplexity) alongside the standard sitemapThe fixed exchange rate (1 EUR = 1.95583 BGN) is set by EU Council regulation and will never change, so the tool stays accurate forever with no maintenance. Happy to share more details about the SEO approach or the technical setup.

news.google.com• Feb 27, 2026• 1 min read

Major Data Brokers Tried to Hide Their Opt-Out Pages From Search Engines - PCMagMajor Data Brokers Tried to Hide Their Opt-Out Pages From Search Engines PCMag

better-hub.com• Feb 26, 2026• 1 min read

Show HN: Better Hub – A better GitHub experienceHey HN,I’m Bereket, founder of Better Auth. Our team spends a huge amount of time on GitHub every day. Like anyone who’s spent enough time there, I’ve always wished for a much better GitHub experience.I’ve asked a lot of people to do something about it, but it seems like no one is really tackling GitHub directly.A couple of weeks ago, I saw a tweet from Mitchell (HashiCorp) complaining about the repo main page. That became the trigger. I decided to start hacking on a prototype to see how far I could push an alternative interface using GitHub’s APIs.Within a week, I genuinely started using it as my default, same with the rest of our team. After fixing a few rough edges, I decided to put it out there.A few things we’re trying to achieve:- UI/UX rethink* – A redesigned repo home, PR review flow, and overview pages focused on signal over noise. Faster navigation and clearer structure.- Keyboard-first workflow: ⌘K-driven command center, ⌘/ for global search, ⌘I opens “Ghost,” an AI assistan

github.com• Feb 25, 2026• 1 min read

Show HN: I treated my CV like a data product-evidence.json,MCP endpoint,llms.txtMost job applications disappear into ATS black boxes. I started wondering: what if my CV was structured well enough that whatever AI sits between me and a recruiter could actually parse it correctly, instead of mangling a PDF?I'm a Not a developer. I built this over a few weeks with Codex+Claude Code.What I ended up with: https://vassiliylakhonin.github.io/The interesting design decisions:Instead of just a PDF, I have six machine-readable JSON files: - resume.json — standard JSON Resume format - evidence.json — maps each claimed metric to its source and verification method. The theory: AI candidate evaluation will increasingly distinguish evidenced claims from unverified ones. - availability.json, capabilities.json, engage.json, verification.json — availability signals, capability profile, intake schema, identity cross-referencesllms.txt points crawlers to the pages that matter. robots.txt explicitly allows GPTBot and OAI-SearchBot. JSON-LD (schema.org ProfilePage/Person) on the homepa

news.google.com• Feb 25, 2026• 1 min read

The New Off-Page SEO Playbook: Links, Mentions & AI Visibility - Search Engine JournalThe New Off-Page SEO Playbook: Links, Mentions & AI Visibility Search Engine Journal

news.ycombinator.com• Feb 25, 2026• 1 min read

Show HN: Turn Instagram and TikTok workouts into executable gym routinesSave workout videos on Instagram or TikTok. Never actually follow them.At the gym, you end up scrolling through saved posts trying to reconstruct sets and reps from a 30-second clip.So I built FitSaver — an iOS app that imports saved workout videos and converts them into structured, editable routines you can actually execute.It doesn’t generate workouts. It doesn’t try to replace trainers.It just turns unstructured social content into something usable.⸻Launched Jan 4. Early numbers: 400 downloads $568 revenue 62% installs from App Store search 13% product page conversion 0 crashes so farThe surprising part: Paying users skew heavily 35–55. I assumed this would be a Gen-Z product because of TikTok usage, but older users seem much more motivated by structure and consistency.Some user feedback:“Saving workout ideas was a mess. This solved that.”“There’s nothing worse than scrolling social media in a busy gym.”“Other apps have preset workouts — this lets me customize.”The broader problem I

aegismind.app• Feb 24, 2026• 1 min read

Show HN: AegisMind Discover – cross-domain hypothesis generation from papersI built a system that reads research papers across unrelated domains and tries to surface hypotheses that neither field would have generated on its own. The Discover page is where it publishes findings: https://aegismind.app/discoveries It's very early — only three discoveries so far — but the core idea is what I want feedback on. The problem it's trying to solve: Science is siloed. A breakthrough in mycology might have direct implications for network routing. A discovery in chronobiology might reframe how we think about database consistency. Nobody reads across all of it, and even when they do, the connection is usually accidental. How it works:The autonomous "Right Brain" service ingests papers across domains continuously Multiple models (GPT, Claude, Gemini, Mistral, Grok) analyze papers in parallel A synthesis layer looks for structural or mechanistic similarities across domain boundaries Hypotheses are only published when they pass a novelty and coherence threshold — it won't surf

indieai.directory• Feb 24, 2026• 1 min read

Show HN: Indie AI Directory – A Curated List of Indie AI ToolsI’m the maker of Indie AI Directory — a purpose-built catalog that highlights independent AI tools, startups, APIs, and experiments built by makers who aren’t backed by big funds or traditional marketplaces.What It IsIndie AI Directory is a searchable, categorized directory of AI tools and resources created by indie developers and solo founders. Each listing includes:A short description of the AI productA link to the tool or landing pageRelevant categories/tags for easier discoveryOptional founder credits and further linksThe site is designed to help:Discover emerging AI tools you may otherwise never findGive indie makers visibility beyond social feed postsConnect builders with early adopters and collaboratorsUnlike most directories that are either static lists or focus only on funded startups, this one prioritizes indie-built AI work.Why It MattersThere’s an explosion of AI tools every day, yet many interesting or useful projects — especially from solo builders — get buried in search

news.ycombinator.com• Feb 23, 2026• 1 min read

Search Console MCP – Unified CLI for Google Search Console, Bing and GA4I built Search Console MCP — a CLI tool that lets you query Google Search Console, Bing Webmaster Tools, and GA4 from a single interface.The problem I kept running into: - Search data lives in one place. - Analytics in another. - Bing in yet another. And automation usually means stitching together brittle scripts or living in dashboards.So MCP does a few simple things:Unified CLI for GSC, Bing, and GA4Consistent query interface across providersScriptable output (JSON-friendly, automation-ready)Designed for pipelines, not dashboardsThe goal isn’t another UI. It’s composable search + analytics data you can pipe into whatever you want — notebooks, internal tools, reports, experiments.A few practical use cases: - Compare query performance across Google and Bing - Map queries → landing pages → conversions - Run automated reporting without touching a browserBuild custom attribution models outside GAIt’s still early, but the core philosophy is: Search data shouldn’t be trapped in web dashboar

rmirror.io• Feb 22, 2026• 1 min read

Show HN: RMirror Cloud – Open-Source OCR and Notion Sync for ReMarkable TabletsI built an open-source cloud service for reMarkable tablets that does three things:Syncs notebooks from your reMarkable to the cloud via a macOS background agent Runs AI-powered OCR on handwritten pages (Claude API, not Tesseract) Pushes transcribed notes to Notion as searchable pages Stack: FastAPI backend, Next.js dashboard, Python agent. Self-hostable. The reMarkable's handwriting recognition (via Connect) is okay for typed-looking text but struggles with real handwriting. I wanted something better that also gave me web access to my notes and pushed them to Notion where I actually work.GitHub: https://github.com/gottino/rmirror-cloud Request beta access: https://rmirror.io/Looking for beta testers — especially people with messy handwriting.

news.ycombinator.com• Feb 22, 2026• 1 min read

Ask HN: How do new blogs break the backlink–indexing loop?We run a small coding blog sharing our learning experience and I keep hitting the same loop: Google won't index most of our pages because the site has no authority. Authority comes from backlinks. But nobody links to a site that doesn't show up in search results. 110+ posts and almost nothing showing up on Google. Bing has started indexing them, but Google won't budge. Google indexed us in the beginning, just a bit, then after one of their updates we were destroyed and never re-covered.We've tried long-form guides, short tutorials, long-tail keywords, competitive keywords, niche topics with zero competition. I'm not sure anymore if content is the problem.We have no noindex issues, no missing sitemaps, no crawl errors — all the basic SEO boxes are checked. Site is submitted to Search Console, PageSpeed Insights performance is good (99% desktop, 85+ mobile).We started cross-posting to Medium, Dev.to, and Hashnode but we can't even be sure that's the right path. We've been posting consist

jeescholar.com• Feb 20, 2026• 1 min read

Show HN: I indexed the academic papers buried in the DOJ Epstein FilesThe DOJ released ~3.5M pages of Epstein documents across 12 datasets. Buried in them are 207 academic papers and 14 books that nobody was really talking about. From what I understand these papers aren't usually freely accesible, but since they are public documents, now they are.I don't know, thought it was interesting to see what this dude was reading. You can check it out at jeescholar.com Pipeline: 1. Downloaded all 12 DOJ datasets + House Oversight Committee release 2. Heuristic pre-filter (abstract detection, DOI regex, citation block patterns, affiliation strings) to cut noise 3. LLM classifier to confirm and extract metadata 4. CrossRef and Semantic Scholar APIs for DOI matching, citation counts, abstracts 5. 87 of 207 papers got DOI matches; the rest are identified but not in major indexes Stack: FastAPI + SQLite (FTS5 for full-text search) + Cloudflare R2 for PDFs + nginx/Docker on Hetzner. The fields represented are genuinely iteresting: there's a cluster of child abuse/groomi

news.ycombinator.com• Feb 16, 2026• 1 min read

Show HN: LLMFeeder – Multi-tab web to Markdown for LLM context (v2.1.0)Hi HN! I shared LLMFeeder here 8 months ago when it was a simple one-click webpage-to-markdown tool. Since then, it's grown into something much more powerful, so I wanted to share the major updates.The original problem: copying documentation/articles to feed into ChatGPT, Claude, or coding assistants like Cursor meant dealing with ads, popups, and navigation clutter and using web mcp server usually bloats the context with irrelevant stuff.v2.1.0 adds several features specifically for LLM power users:- Multi-tab support: The #1 requested feature. Select multiple tabs with Ctrl/Cmd+Shift+Click, then convert all at once. Options: copy merged, download merged, or download as ZIP with separate files per tab. Great for research sessions where you need context from multiple sources!- Right-click context menus: No need to open the popup. Just right-click anywhere on a page → "Copy to Markdown". When multiple tabs are selected, you get batch options in the menu.- Token counter: Real-time estima

github.com• Feb 7, 2026• 1 min read

Show HN: I built a RAG engine to search Singaporean lawsI built a "Triple Failover" RAG for Singapore Laws, then rewrote the logic based on your feedback.Hi everyone!I’m a student developer. Recently, I created Explore Singapore, a RAG-based search engine that scrapes about 20,000 pages of Singaporean government acts and laws.I recently posted the MVP and received some tough but essential feedback about hallucinations and query depth. I took that feedback, focused on improvements, and just released Version 2.Here is how I upgraded the system from a basic RAG to a production-grade one.The Design & UI I aimed to avoid a dull government website.Design: Heavily inspired by Apple’s minimalist style.Tech: Custom frontend interacting with a Python backend.The V2 Engineering OverhaulThe community challenged me on three main points. Here’s how I addressed them:1. The "Personality" Fix Issue: I use a "Triple Failover" system with three models as backup. When the main model failed, the backups sounded entirely different.The Solution: I added Dynamic S

news.ycombinator.com• Feb 4, 2026• 1 min read

From building client websites to launching my own SaaSI didn’t start with SaaS. I started by building websites WordPress for survival.My first real projects were simple sites — landing pages, directories, small tools. One of them grew into Around md — a platform that helps people discover restaurants, parks, and interesting places in their city.No VC. No team.Just real users searching for where to go and what to explore around them. Later, I officially opened my company — dricomm.comSounds fancy. Reality was not. Analytics… It was: • clients asking “why numbers don’t match” • analytics dashboards nobody trusted • GDPR emails every few months • cookie banners everywhere • and GA4… always GA4Every site I launched had the same issue: analytics data never felt real. Pageviews were lower than expected. Funnels didn’t make sense. Marketing decisions were based on “best guesses”.And the moment you add a cookie banner — boom: 30–50% of users disappear from your data.At some point I realized something uncomfortable: I don’t actually know what’s ha

news.ycombinator.com• Feb 3, 2026• 1 min read

Ask HN: What's your competitive intelligence workflow as a small team?I've been researching how founders track competitors and the tooling landscape is interesting. Enterprise teams use Klue/Crayon ($20K+/yr), mid-market uses Competitors.app ($15-20/competitor/mo), and everyone else seems to use... Google Alerts and hoping for the best?Curious what actually works for small teams:- Do you actively monitor competitors, or just check in occasionally? - What signals matter most? (pricing changes, feature launches, hiring, funding?) - Is the raw data useful, or do you need someone to interpret "competitor X changed their pricing page" into "here's what this means for you"?I keep hearing founders say they got blindsided on sales calls by competitors they didn't know existed. Wondering if this is a real pain point or just something people complain about but don't actually prioritize.

lingocoder.com• Feb 3, 2026• 1 min read

Show HN: Clod.ai – A Literal Wayback in Time Machine in Figuratively No TimeI discovered a free online Pomodoro timer in 2018. [1] I'd been a frequent user of it from then until it was decommissioned in early '25. I found it super helpful for timeboxing stuff within easy-to-commit-to intervals.About a month ago, I started having really intense hunger pangs for it.A few pages of the original implementation are archived on the Wayback Machine. A couple weeks ago, I got the idea to reverse-engineer it using those pages as a reference.That's when I started researching what the Claude Code fuss was about. I wasn't then and am still not ready to spend money on AI. So, when I stumbled on the free Claud.ai, I figured I'd test it out on my reverse-engineering idea.I used Copilot, Sourcegraph's Cody Visual Studio Code agent and ChatGPT a decent amount last year. More recently I've been using Gemini Code Assist. But this project was my first time ever using Claud.ai.I guess Claude.ai in the browser uses React and Tailwind CSS for building web apps. I'm not a frontend dev

news.google.com• Jan 30, 2026• 1 min read

PageIndex redefines RAG with tree search - VentureBeatPageIndex redefines RAG with tree search VentureBeat

sentienceapi.com• Jan 28, 2026• 1 min read

A verification layer for browser agents: Amazon case studyA common approach to automating Amazon shopping or similar complex websites is to reach for large cloud models (often vision-capable). I wanted to test a contradiction: can a ~3B parameter local LLM model complete the flow using only structural page data (DOM) plus deterministic assertions?This post summarizes four runs of the same task (search → first product → add to cart → checkout on Amazon). The key comparison is Demo 0 (cloud baseline) vs Demo 3 (local autonomy); Demos 1–2 are intermediate controls.More technical detail (architecture, code excerpts, additional log snippets):https://www.sentienceapi.com/blog/verification-layer-amazon-...Demo 0 vs Demo 3:Demo 0 (cloud, GLM‑4.6 + structured snapshots) success: 1/1 run tokens: 19,956 (~43% reduction vs ~35k estimate) time: ~60,000ms cost: cloud API (varies) vision: not requiredDemo 3 (local, DeepSeek R1 planner + Qwen ~3B executor) success: 7/7 steps (re-run) tokens: 11,114 time: 405,740ms cost: $0.00 incremental (local inference) vi