bifrost
by maximhq
Bifrost is a gateway that sits between your apps and AI providers such as OpenAI, Anthropic and AWS Bedrock, offering one OpenAI-compatible API for all of them. It handles failover, load balancing, caching, spending limits and access keys so you can manage AI usage in one place.
- Stars
- 9.1k
- Licence
- Apache-2.0
- Runs on
- A small server
- Setup
- Easy
- Language
- Go
- Age
- 587 days
What you can do with it
- Send requests to many AI providers through a single OpenAI-compatible API
- Set automatic fallbacks and spread load across several API keys so your app stays up
- Create virtual keys with budgets and rate limits for teams or customers, and track usage in a web dashboard
Make money with it
A freelancer could set up and manage a gateway for clients, giving each their own virtual key and budget, as a paid AI infrastructure service.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Cut AI costs by caching similar responses and capping spend per team or client with budgets
- Keep a customer-facing AI feature running by failing over to another provider when one goes down
Can you use it commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Run it with "npx -y @maximhq/bifrost" or "docker run -p 8080:8080 maximhq/bifrost", then configure providers in the web interface at localhost:8080.
Follow the official instructions in the project README.
Things to check
- You still need your own paid API keys for the AI providers
- Some features (clustering, guardrails, adaptive load balancing, the MCP gateway) are described as enterprise-only
- The README was truncated, so the full licence split between open-source and enterprise features is unclear
Who's talking about it
- Rost (rosgluk): Trending Open Source AI Projects on GitHub, October 2026 Featured in a roundup
- Rost Glukhov: Trending Open Source AI Projects on GitHub, October 2026 Featured in a roundup
Checked 27 Oct 2026. Summary drafted by AI from the project's README.