Albert-Weasker/niubigeo

Open-source AI brand visibility and competitor reports. Official website: https://niubigeo.ai/ | Paid services: AI testing by real people and GEO optimization. Pricing: https://niubigeo.ai/pricing

What it solves

NiubiGEO helps product founders and marketing teams understand their brand's visibility within AI-generated answers. It addresses the problem where a product may be indexed by traditional search engines but is ignored, misunderstood, or superseded by competitors when users ask LLMs for recommendations or alternatives.

How it works

Users provide a domain or product page, and the system identifies the brand, its category, and potential competitors. The user then confirms a set of customer-centric questions. NiubiGEO calls configured AI provider APIs (such as OpenAI, Anthropic, or Perplexity) to generate answers to these questions. Finally, it analyzes the responses to determine if the brand is mentioned, how it is described, who the competitors are, and which sources the AI cited to reach those conclusions.

Who it’s for

It is designed for founders and teams who want a self-hosted, open-source way to audit their AI visibility and verify the evidence behind AI recommendations without relying on expensive SaaS subscriptions.

Highlights

  • Multi-Provider Support: Integrates with OpenRouter, OpenAI, Anthropic, Google Gemini, Perplexity, and DeepSeek.
  • Evidence-Based Reporting: Every conclusion in the report links directly back to the original AI answer and citation sources.
  • Self-Hosted & BYOK: Allows users to run the tool locally via Docker or Node.js using their own API keys.
  • Bilingual Support: Full support for English and Simplified Chinese across the interface, prompts, and analysis.

Related

  • Project
    hi-godot/godot-ai

    A plugin that connects MCP-compatible AI assistants to the Godot editor, allowing agents to build scenes, edit nodes, and configure game environments in real-time.

  • Project
    moj-analytical-services/splink

    A Python package for probabilistic record linkage and deduplication that identifies and links records without unique identifiers using the Fellegi-Sunter model.

  • Project
    shepherd-agents/shepherd

    A runtime substrate for AI agents that provides secure sandboxing, reversible execution traces, and a review-and-approve workflow for all filesystem changes.

  • Project
    LoRexxar/Kunlun-M

    An open-source static code security analysis system that uses AST graphs and taint analysis to detect vulnerabilities across 14 different programming languages.