Semantic Routing Python Packages

oiax

Semantic policy routing for agent fleets — delivers the right governance context by meaning, per-turn, harness-agnostic

kayak

Classify, route, and rank text in Python with self-hosted models. Typed decisions and evaluation.

python-rerouting-library

A lightweight Python library for semantic model routing between local quantized Llama on CPU and cloud LLMs with uncertainty handling and fallback.

mcp-sieve

Semantic tool selection proxy for MCP servers — LLM sees 2 tools instead of dozens

semroute

A flexible and easy to use tool for Semantic Routing

kvfleet

KV-cache-aware intelligent routing for self-hosted and hybrid LLM fleets. Route requests using model quality, latency, cost, policy, and live GPU state.

synaptoroute

A high-throughput semantic routing engine for AI agents and LLM applications. Executes local intent classification using ONNX embeddings, FAISS indexing, and asynchronous micro-batching.