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.

What it solves

It solves the problem of discovering new AI models, products, and tools before they become visible in traditional keyword research tools. Because keyword tools typically rely on lagging indicators like Google Trends, this project identifies "surging" terms the moment they appear on social media, code repositories, or sitemaps, allowing users to capture SEO opportunities and stay ahead of the curve.

How it works

The system monitors four primary signals to identify new terms:

  1. Social & Community: Tracks specific X (Twitter) accounts and Hugging Face's trending list for new names.
  2. Code Repositories: Detects GitHub "breakouts" (repos under 14 days old with high star growth).
  3. Web Indexing: Analyzes sitemaps for recurring new words and identifies newly registered domains that rank for multiple keywords.
  4. Direct Traffic: Integrates with Google Search Console to find new queries bringing impressions to the user's own site.

These leads are then processed by a "Name Judge" (an LLM) to filter out common words. For high-confidence names, it generates a "Keyword Table" that maps the specific product name to the generic search terms (e.g., mapping "SynthID Detector" to "ai image detector") to determine which existing demands the new tool serves. Finally, it performs a 14-day review using Google Trends to verify if the term actually rose in popularity.

Who it’s for

  • SEO Specialists: People building AI tool directories or landing pages who need to rank for new terms quickly.
  • Newsletter Authors: Curators who want to report on new AI tools the day they launch.
  • Product Managers: Those tracking competitors and emerging trends in the AI space.

Highlights

  • Multi-signal Detection: Combines X, Hugging Face, GitHub, sitemaps, and Search Console for comprehensive coverage.
  • Generic Term Mapping: Uses LLMs to translate specific brand names into high-volume generic keywords.
  • Automated Verification: Includes a built-in 14-day feedback loop to check hit rates against Google Trends.
  • Low-Cost Infrastructure: Designed to run via GitHub Actions using a single API key (AIsa) for most functions.

Related

  • Project
    aeonfun/opendia

    An open-source MCP server and browser extension that lets AI models control your browser using your existing logged-in accounts and session data.

  • Project
    IPADS-SAI/MobiAgent

    MobiAgent is an open‑source framework for running LLM‑based mobile agents on Android/HarmonyOS devices. It provides the MobiMind model family, an Agent Record‑&‑Replay system (AgentRR), and the MobiFlow benchmark. The repo includes on‑device inference support, multiple memory modules (user‑profile, experience, action), a multi‑task runner that controls phones via ADB, and a ready‑to‑install Android app. Detailed setup steps, model deployment instructions, and citation info are provided.

  • Project
    FatihMakes/Mark-LVI

    Mark LVI is a cross‑platform desktop AI assistant with voice, avatar, vision and OS‑control features. It can use Google Gemini Live or any local/hosted LLM (Ollama, OpenAI, etc.) together with Whisper for speech‑to‑text and Piper/ElevenLabs for text‑to‑speech. The UI lets you swap engines, add plugins, and manage memory, while safety guards ensure the assistant only reports verified actions.

  • Project
    team9ai/team9

    A collaborative workspace for AI agents and humans to work together in shared channels and documents, built on the OpenClaw ecosystem.