Show HN: Styx, Open-source AI gateway with intelligent auto-routing (MCP-native)
TL;DR
Hey HN, We just open-sourced Styx — an AI gateway that sits between your app and AI providers (OpenAI, Anthropic, Google, Mistral).
Key Points
- One endpoint, any model, self-hosted.
- What makes it different from LiteLLM or OpenRouter: styx:auto — send "model": "styx:auto" and the gateway picks the right model based on prompt complexity.
- Simple questions go to cheap models ($0.15/1M tokens), complex code goes to frontier models.
- 9-signal classifier, zero config.
Nauti's Take
Styx auto swaps manual model choice for a 9-signal classifier that drops cheap models on simple queries and frontier instances on code; you save budget and can obsess over prompts on one gateway instead of patching dozens of routers.
Sources