Any AI Proxy API

Any AI Proxy API is a self-hosted gateway that exposes browser-only AI services as an OpenAI-compatible API endpoint.

  • AI
  • Home Automation
Any AI Proxy API is a self-hosted gateway that exposes browser-only AI services as an OpenAI-compatible API endpoint. It drives the provider's web interface automatically so existing OpenAI clients, scripts, and agents can call other models without an official developer key. It suits homelab users who want to route multiple AI providers through one consistent API format.

Platform availability

Available on 0 of 10 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

43/100 Fair

Maintained
72last commit 32 days ago
Popular
2927 GitHub stars
Easy to install
250 install platforms, install notes, Docker image
Light to run
No data
Security check
201 serious finding, 4 minor, CI

Based on 4 of 5 factors.

GitHub stars
27
Open issues
1
Last commit
2026-10-20
Latest release
v2.1.1
License
Apache-2.0
Activity
stale

Checked 3 days ago - source: GitHub (AI-QL/api-proxy)

Resources & Compatibility

ARM (e.g. Raspberry Pi) is supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Fill in your config file first Set the database address, your master key (the admin password), and the secret access keys for AI services (API keys) in your config file. If these are missing or wrong, the gateway will not start properly or connect to services like OpenAI or Gemini. source
  • Install Docker and Docker Compose If you are installing with Docker (the software that runs the app in a container), install Docker and Docker Compose first, then copy the example config to docker/config.yml. Without them, the Docker setup commands will fail and the app will not run. source
  • Start the gateway with your config Run the gateway by pointing it at your finished config file, such as any-llm-gateway serve --config config.yml. This tells the app where to find the database, admin key, and AI provider settings it needs. source

Fetched 53 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

How do I start the default Docker instance and change its port or target?

Run the Docker image with port 9017 mapped to the container. You can override the server port and target endpoint with the PORT and TARGET environment variables; the defaults are 9017 and the OpenAI API target.

Can I send a custom Host header to a backend whose domain differs from the URL?

Yes. Set the HOST environment variable to define a different Host header. If it is not set, the host is inherited from the target URL.

Can the proxy expose a backend that does not include CORS headers?

Yes. It is intended to bypass CORS restrictions so private APIs without CORS headers can be accessed through the proxy.

Does it support bypassing TLS certificate validation for internal self-signed certificates?

Yes. It lists TLS certificate validation bypass as a use case for enterprise internal self-signed certificates. The SECURE variable defaults to true to enable TLS validation security features.

I was using the older Docker image; is it still available after the current release?

The previous Docker image for version 2.0.0 and below is still available at the old image name. The current repository uses the api-proxy image for new deployments.

Answers sourced from github.com

Community

Collected 48 days ago - public community threads