semantic-router

A programmable Mixture-of-Models router for heterogeneous LLM inference

Categories & Topics

ai-gatewaybert-classificationfine-tuninggolanghuggingface-candlehuggingface-transformerskubernetesllmllmroutermixture-of-modelspii-detectionprompt-engineeringprompt-guardrustsemantic-routervllm

Visit Website View on GitHub

Repository Stats

5.1k

GitHub Stars

812

Forks

5.1k

Watchers

337

Open Issues

License

Apache License 2.0

Repository

vllm-project/semantic-router

Last Updated

Today

August 13, 2026

Latest Release

Top Contributors

View all contributors →

Related Tools

9router

25k

Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.

bumblebee

4.9k

Read-only developer endpoint scanner for on-disk package, extension, and developer-tool metadata, built to check exposure to known software supply-chain compromises.

can-i-finetune-this

792

Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.

cli-printing-press

4.4k

Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compound insight commands.

CliRelay

907

Self-hosted AI gateway for coding CLIs — one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tenant web console, request logs, and spend quotas.

Confucius4-TTS

742

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine