MIT License

Open Source AI Visibility Engine

Genwolf's core evaluation engine is open source under the MIT license. Inspect how AI visibility is measured. Run it locally. Deploy it in your own infrastructure.

Why we open-sourced Genwolf

AI visibility tools shouldn't be black boxes. If you can't inspect the evaluator, you can't trust the metric.

Measuring brand presence in AI-generated answers requires:

  • Clear evaluation logic
  • Repeatable prompt execution
  • Transparent detection rules

By open-sourcing the core engine, we make the methodology inspectable and extensible.

Every team has a different tech stack, different internal tools, and different workflows. A one-size-fits-all SaaS can't always account for that.

With Genwolf as an open core, you can build your own integrations on top — connect it to your CI pipelines, internal dashboards, Slack alerts, or custom reporting. Treat Genwolf as the engine and shape everything around it to fit your workflow.

You also get full freedom over the model layer. Swap in local LLMs, private endpoints, or any provider you want. It's your infrastructure, your models, your rules. The only costs are your own infrastructure and the LLM API usage you choose to run.

What's included

The open-source version includes everything you need to run the full stack locally using Docker Compose.

AI prompt execution worker
Brand mention detection logic
Citation extraction
PostgreSQL persistence
Docker-based deployment
Support for OpenAI, Gemini, and Perplexity

OSS vs Hosted Genwolf

Open SourceHosted
HostingSelf-hostedFully managed
InfrastructureRequires own setupNo infrastructure required
SetupManual configurationInstant access
API keysManaged by youSecurely managed
SupportCommunityDedicated product support

The hosted version is built on top of the same open core, with additional reliability, scaling, and UX improvements.

Deployment Model

Genwolf OSS is:

  • Single-tenant by default
  • Designed for internal team deployments
  • Horizontally scalable on the worker layer
  • Stateless on the web layer

Contributing

We welcome contributions in:

  • Provider integrations
  • Detection improvements
  • Performance optimizations
  • Documentation

Ready to explore the source?

Clone the repo, spin up Docker Compose, and start inspecting how AI visibility is measured.

View on GitHub