LocalLeads by PostOrbit
Built for the AI-native sales stack via a native MCP server.
What it does
Local Leads is an MCP server that brings Google Maps and local business data straight into your AI chat. Search any niche and location, pull real businesses, enrich them with verified emails, and walk away with a clean cold-outreach list — all in conversation, no scraping tools or CSV wrangling.
Google Maps data turned into verified lead data — every business scored 0–100 before you pay. Native MCP for Claude & Cursor. From €4/mo (annual). Free to try, no signup.
Search any niche and city. Get verified local businesses pre-scored 0–100 — so you only pay credits for the leads worth contacting. The whole product: what a scored lead looks like, what the ICP filter throws away, and what it costs. Every number shown is one the product produces. Narration is synthetic. Every lead in your dashboard ships with a deterministic 0–100 Quality Score, computed from the Google Maps data we have at search time — phone, website, reviews, rating, hours, photos, freshness. Running email enrichment further refines the score by adding the email signal. Sort, filter, and gate your credit spend on the businesses that can actually be reached. Sample card — your dashboard…from postorbit.io
Does the same job
all alternatives →More growth this month
the category →
AstraPixels▲267A pixel-art solar system at its real current positions.
Growth · 29d ago · astrapixels.com

Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io


- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io


I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com