Back to directory

new-term-radar

In a curated listMaintenance: Active

zhuyansen/new-term-radar

Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.

View on GitHubHomepage
$ dsh plugin add new-term-radar

Install

dsh has no central install command — add this plugin’s entry (documented in its README) to your profile or patch config, then restart.

How installs work

2,202

stars

651

forks

Python

Language

MIT

License

2026-10-12

Created

2026-11-19

Last push

README

new-term-radar logo: a radar sweep catching a new blip

new-term-radar

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

PyPI Python License: MIT Stars Forks Downloads Last commit

MCP Registry Tessl registry LobeHub Security-graded by Agent Skills Hub Cursor Directory ClawHub skills.sh

⭐ 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. In the one case checked so far, Strata, the radar named it three days before its rise in DataForSEO Trends (what we measured).

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.

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

How the radar works: six signals, a name judge, the keyword table with its page-one check, a daily report and a 14-day check; used from the command line, three Agent Skills, an MCP server or the pains command. What 0.6.0 added is purple and tagged NEW

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.

Read the full README on GitHub →

DSH Plugins is an independent community directory of DeepSeek Harness plugins. Not affiliated with or endorsed by DeepSeek. Third-party plugins are not security-audited — review the source before installing.

New DeepSeek Harness plugins, weekly. No spam.