Bifrost

We’re excited to launch Bifrost, the fastest and open-source LLM gateway At Maxim, our internal experiments with multiple gateways for our production use cases quickly exposed scale as a bottleneck. And we weren’t alone. Fast-moving AI teams echoed the same frustration -- LLM gateway speed and scalability were key pain points. They valued flexibility and speed, but not at the cost of efficiency at scale. This motivated us to build Bifrost -- a high-performance LLM gateway that delivers on all fronts. Written in pure Go, Bifrost adds just 11μs latency at 5,000 RPS, and is 40x faster than LiteLLM. Key features: 🔐 Robust governance: Rotate and manage API keys efficiently with weighted distribution, ensuring responsible and efficient use of models across multiple teams 🧩 Plugin first architecture: No callback hell, simple addition/creation of custom plugins 🔌 MCP integration: Built-in Model Context Protocol (MCP) support for external tool integration and execution The best part? It plugs in seamlessly with Maxim, giving end-to-end observability, governance, and evals, empowering teams to ship AI products with the reliability and speed needed for real-world use. We’re super excited to have you try it and share your feedback! You can get started today at getmaxim.ai/bifrost.