new-term-radar

Catch the names AI people are about to search for, the day they appear, before keyword tools list them.

⭐ 700+ stars on its first day, 1,000 in just over three · on PyPI, the official MCP Registry, Cursor Directory, LobeHub, Tessl, ClawHub and skills.sh

Quick start · What it reads · The keyword table · Agents and MCP · config.json · 中文说明

A daily report of the names that are starting to surge in AI: new models, products, tools and repos, caught where they are said first, before they show up in keyword tools.

Built for people who make pages, posts or products around new terms: SEO for AI tool sites, newsletters, directories, anyone who wants to know about "Strata" or "Seedance" the day it appears and not two weeks later.

Why

A new name leaves a trail, in this order:

1. A lab or a well-followed account says it on X; a model enters Hugging Face's trending list.
2. One GitHub repo takes off on its own.
3. Directories and competitors add pages for it; someone registers a domain for it and the site starts to rank.
4. Your own site gets its first search impressions for it.
5. Google Trends shows the curve, days or weeks later.

Keyword tools read step 5. This radar reads steps 1 to 4 every day and uses step 5 only to check itself.

One example it was built around: Niko1221/Strata was created on 2026-09-24 and had 7,700 stars nine days later. People were searching "niko strata" from 9/26, while no second repo carried the name and no keyword tool listed it. A single repo gaining 800 stars a day is the whole signal, and it is public.

What it reads

Purple, tagged NEW: what 0.6.0 added. On the keyword table: word age, markets, page-one shape, the twelve months, your own rank, what else holds page one (threads, an AI overview) and the exact-match .com. The first words ③'s new sites rank for, what ChatGPT recommends for ⑦'s asks, three more payment platforms and the builders on ⑧, ⑨ just listed, ⑩ money and the evidence beside the names. All of it is in CHANGELOG.md.

This is the beginning of the README. Read the rest at the original. Read the full README ↗