maximhq/bifrost
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
GitHub repository with 5,488 stars and 692 forks.
Language: Go
Topics: ai-gateway, gateway, gateway-services, generative-ai, guardrails, llm, llm-cost, llm-gateway, llm-observability, llmops