This project is scheduled for launch
Launch date: Monday, August 17, 2026 at 08:00 AM UTC
Scheduled
GreyFox, from Skilful Fox Independent research studio, is a powerful, self-hosted control plane for applied AI systems, designed to manage and secure local AI application traffic. It functions as a telemetry-free proxy, enabling developers and local operators to inspect, debug, and enforce policies on LLM data streams without sending sensitive operational data to the cloud.
Key Features:
GreyFox is ideal for developers and teams conducting local AI experiments, offering a controlled environment to reason about AI traffic paths. It allows for the inspection of requests and responses, helping to understand model interactions and fine-tune application behavior before deployment. By centralizing proxy flows, it eliminates scattered configurations across multiple scripts, streamlining the development process.
Furthermore, GreyFox serves as a critical tool for enforcing data privacy and security policies within AI applications. Organizations can leverage its self-hosted nature to ensure that sensitive LLM data remains within their Docker environment, meeting compliance requirements. The Essential edition extends this by providing managed user controls and advanced analytics, making it suitable for repeatable local AI routing setups and deeper traffic analysis for teams.
Pricing Information:
GreyFox offers a free, open-source Community Edition for basic local AI traffic inspection. The Essential commercial edition is available via monthly (EUR 19) or annual (EUR 179) subscriptions, processed externally by Stripe, providing advanced features like managed users and analytics. A Pro edition with enterprise-grade audit and programmable routing is currently in development.
User Experience and Support:
The GreyFox interface is a local operator panel, not a cloud-hosted surveillance layer, designed for intuitive self-hosted control. It provides clear views of local routing, users, providers, and usage signals. The UI includes features like traffic history, user management, and provider settings. Support is available via email at support@skilful-fox.com.
Technical Details:
GreyFox operates as a local proxy server, integrating seamlessly by simply changing the base URL of any OpenAI-compatible LLM client to point at its local endpoint. It runs within a Docker environment, ensuring self-containment. The package is published through GitHub Container Registry, making installation straightforward from the command line.
Pros and Cons:
Key Features:
- Self-hosted, telemetry-free control plane for AI traffic.
- Local proxy for OpenAI-compatible LLM providers.
- Inspect, debug, and enforce policies on LLM data streams.
- Comprehensive operator panel with traffic history, user control, and provider settings.
- Manual route overrides and policy-oriented local controls.
- Community, Essential, and Pro editions catering to various workflow needs.
GreyFox is ideal for developers and teams conducting local AI experiments, offering a controlled environment to reason about AI traffic paths. It allows for the inspection of requests and responses, helping to understand model interactions and fine-tune application behavior before deployment. By centralizing proxy flows, it eliminates scattered configurations across multiple scripts, streamlining the development process.
Furthermore, GreyFox serves as a critical tool for enforcing data privacy and security policies within AI applications. Organizations can leverage its self-hosted nature to ensure that sensitive LLM data remains within their Docker environment, meeting compliance requirements. The Essential edition extends this by providing managed user controls and advanced analytics, making it suitable for repeatable local AI routing setups and deeper traffic analysis for teams.
Pricing Information:
GreyFox offers a free, open-source Community Edition for basic local AI traffic inspection. The Essential commercial edition is available via monthly (EUR 19) or annual (EUR 179) subscriptions, processed externally by Stripe, providing advanced features like managed users and analytics. A Pro edition with enterprise-grade audit and programmable routing is currently in development.
User Experience and Support:
The GreyFox interface is a local operator panel, not a cloud-hosted surveillance layer, designed for intuitive self-hosted control. It provides clear views of local routing, users, providers, and usage signals. The UI includes features like traffic history, user management, and provider settings. Support is available via email at support@skilful-fox.com.
Technical Details:
GreyFox operates as a local proxy server, integrating seamlessly by simply changing the base URL of any OpenAI-compatible LLM client to point at its local endpoint. It runs within a Docker environment, ensuring self-containment. The package is published through GitHub Container Registry, making installation straightforward from the command line.
Pros and Cons:
- Pros:
- Telemetry-free and self-hosted for maximum data privacy.
- Provides granular local control over AI application traffic.
- Supports OpenAI-compatible LLM providers with easy integration.
- Offers a free Community Edition and scalable commercial options.
- Advanced analytics and user management in paid editions.
- Cons:
- Requires explicit routing of traffic through its proxy.
- Advanced Pro features are still under development.
- Manual cost estimates in Community Edition, not authoritative token monitoring.
- Not designed as generic enterprise software, focused on local operator workflows.
- Conclusion:
GreyFox empowers developers and operators with a robust, privacy-first solution for managing and securing their local AI application traffic. Its self-hosted, telemetry-free approach ensures complete control and transparency over LLM data streams. Explore the Community Edition today to take charge of your AI workflows and build with confidence.
Comments
Comments will be available once the project is launched.
Publisher
Skillful Fox
Launch Date2026-08-17
Platformweb
Pricingfreemium
Tech Stack
#TypeScript#Docker
Sponsors
AIChatOne
All-in-one AI assistant with the most advanced AI models to help you Chat, Search, Write, Read and more.
Become a Sponsor
Get your brand featured here