Radar check
What we found when we opened it. Every bar is one fact, with its date.
Last code pushed 26 Oct 2026, the same day before this check.
Latest release v0.3.28 on 25 Oct 2026.
Public since May 2026, 5 months.
38 stars and 2 forks.
251 commits and 1 new issues in the last 90 days.
2 contributors. 197 pull requests merged in 90 days. A small team carries it.
A security policy says how to report a problem. No published security advisories.
How the bars are scored
- Alive. Days since the last code push: a week or less 100, a month 90, three months 70, six months 50, a year 30, eighteen months 15, older 0.
- Releases. Age of the latest GitHub release, on a similar scale; no bar when the project publishes no releases.
- Maturity. Age of the project: eight years 100, five 90, three 70, two 55, one 40, six months 25, younger 10.
- Adoption. Stars on a log scale: 100,000 stars is 100, 10,000 is 80, 1,000 is 60, 100 is 40.
- Activity. Commits in the last 90 days: 300 or more 100, 100 85, 30 65, 10 45, any 25.
- Community. People who have contributed: 100 or more 100, 30 80, 10 60, 5 40, 2 25, one 10.
- Security. A published security policy 80, none 40; published advisories are listed, not scored.
Checked by Repo Radar on 26 Oct 2026 from the repository on GitHub.
In simple English
When people ask AI search engines for recommendations, does your brand appear? This tool checks how often major AI models mention your product or service. It runs locally on your computer and connects directly to your AI coding assistant. You can see which answers name your brand, where your competitors show up, and what content you are missing. It is free to use, though you pay for the AI provider requests you make.
What it is
An open-source Model Context Protocol server that tracks brand visibility and citations across multiple generative search engines. It exposes tools that an AI assistant can run to scan prompts, compare competitors, and generate visibility scores.
What it is good for
Solo founders and marketers who want to measure and improve their visibility in AI-generated answers without paying for external enterprise platforms.
- Integrates with dozens of AI clients and coding tools.
- Runs locally on your machine with your own API keys.
- Includes pre-built tool definitions for automated brand tracking.
- Requires valid API keys for the AI engines you want to scan.
- Node.js 22.13 or newer is required on your machine.
- Scanning multiple prompts across seven engines costs real money in API fees.
Manual searches across multiple AI chat interfaces to see if your brand is recommended.
Claude Desktop or Cursor, where you can chat with the server directly.
- modelcontextprotocol/servers92k stars
A collection of official and community MCP servers for connecting various tools to AI assistants.
- GoogleChrome/lighthouse-ci7.1k stars
Runs the standard page audit on every code change and fails the change if the page got slower.
- harlan-zw/nuxt-seo1.5k stars
Seven search-engine and answer-engine modules for Nuxt sites, installed as one package.
- Swetrix/swetrix1.2k stars
Website analytics with no cookies, plus performance monitoring and error tracking, which you can host yourself.
npx -y @digestseo/mcp-geo