Repolode
Submit
elmohq

elmohq/elmo

Self-hosted open-source platform that tracks how AI answer engines like ChatGPT, Claude, Perplexity and Gemini mention and cite your brand.

Open-source alternative to:ProfoundOtterly.aiPeec AI

View on GitHubWebsite
Stars
479
Forks
112
Open issues
135
Last commit
4 hours ago

What is it?

Elmo is a platform for measuring and improving AI visibility, also called Answer Engine Optimization (AEO) or Generative Engine Optimization (GEO). You define prompts a potential customer might ask an AI assistant, and Elmo runs them on a schedule against engines such as ChatGPT, Google AI Overviews, Gemini, Perplexity, Copilot, and Claude or Grok through direct model APIs.

Each answer is parsed for your brand name, aliases, domains and competitors, and mentions are scored with sentiment and ranking position. Cited URLs are stored and grouped by domain and category, so you can see which sources the engines rely on. Raw responses are kept in PostgreSQL, and the scoring code lives in the repository so every metric can be audited.

The project ships as a Docker Compose stack installed through an npm CLI, and includes a REST API with TypeScript and Python SDKs and an MCP server for coding assistants. Shareable reports can be viewed without an account.

Key features

  • 01Tracks brand mentions and citations across ChatGPT, Perplexity, Gemini, Claude and Google AI Overviews.
  • 02Scores visibility, share of voice and sentiment per prompt, model and competitor.
  • 03Categorizes cited URLs by domain, including your own sites, competitors and social media.
  • 04Records the web searches engines run while answering, showing query fan-out.
  • 05Stores raw engine output in PostgreSQL so metrics can be re-derived and audited.
  • 06Provides a REST API, TypeScript and Python SDKs, and an MCP server.

Use cases

  • Marketing teams tracking how AI assistants describe their brand against competitors.
  • Agencies running AEO reports for multiple clients with white-label deployments.
  • Companies that want AI visibility data kept in their own infrastructure.
  • Developers querying AI visibility data from coding assistants through MCP.

Quick start

  1. 1

    Install the Elmo CLI globally

    npm install -g @elmohq/cli
  2. 2

    Run the interactive setup wizard to create configuration

    elmo init
  3. 3

    Start the Docker Compose stack

    elmo compose up -d
  4. 4

    Open http://localhost:1515 in your browser and create an account

Things to know

  • Requires API keys for at least one AI provider or scraper, plus a TypeSafe key for Jev.
  • Running the tracking costs money per answer judged, on top of self-hosting effort with Docker Compose.

Topics

#ai-visibility#answer-engine-optimization#generative-engine-optimization#seo#self-hosted#postgresql#typescript#mcp#aeo#ai-engine-optimization

FAQ

What is elmo?
Self-hosted open-source platform that tracks how AI answer engines like ChatGPT, Claude, Perplexity and Gemini mention and cite your brand. Elmo is a platform for measuring and improving AI visibility, also called Answer Engine Optimization (AEO) or Generative Engine Optimization (GEO). You define prompts a potential customer might ask an AI assistant, and Elmo runs them on a schedule against engines such as ChatGPT, Google AI Overviews, Gemini, Perplexity, Copilot, and Claude or Grok through direct model APIs.
Is elmo free to use? What license does it have?
elmo is open source under the MIT license. Check the license terms before using it in commercial products.
Is elmo still maintained?
Actively maintained. The last commit to elmo was on Oct 22, 2026.
What can I use elmo for?
Marketing teams tracking how AI assistants describe their brand against competitors. Agencies running AEO reports for multiple clients with white-label deployments. Companies that want AI visibility data kept in their own infrastructure. Developers querying AI visibility data from coding assistants through MCP.
How do I install elmo?
Install the Elmo CLI globally: npm install -g @elmohq/cli Run the interactive setup wizard to create configuration: elmo init Start the Docker Compose stack: elmo compose up -d Open http://localhost:1515 in your browser and create an account
Where can I get elmo?
The source code and installation instructions are on GitHub: https://github.com/elmohq/elmo

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects