An open, programmable decision layer for models and compute.
vLLM Semantic Router is a programmable routing layer that chooses or combines language models for each request in a system using multiple models and types of computing infrastructure. It helps teams route inference by signals such as user preferences, application policies, quality, cost, latency, privacy, and safety requirements. The catalogue skills and instructions support configuring and operating this model-routing system.
Latest release v0.4.0 — Release v0.4.0 · 27 Sept 2026
2 files for GitHub Copilot, Codex and OpenCode: semantic-router copilot-instructions.md, semantic-router AGENTS.md — 1,164 tokens loaded in every session.
.github/copilot-instructions.md A 196 tok AGENTS.md A 968 tok These files are vllm-project/semantic-router's own configuration — they tell GitHub Copilot, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.