aurelio-labs/semantic-router

Health v2 · maintenance only

Adoption not part of the score

3841 stars · 365 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Semantic Router is a Python library that provides a fast decision-making layer for LLMs and agents, routing requests based on semantic vector similarity instead of slow LLM inference. It supports static and dynamic routes, guardrails, multi-modal (image) routing, and both cloud and fully local execution via various embedding and LLM integrations.

Use cases

• route user queries to the right agent tool without an LLM call
• build guardrails to keep a chatbot away from political topics
• classify incoming support tickets by intent in milliseconds
• decide whether a message needs RAG retrieval or chitchat handling
• run a fully local router with HuggingFace embeddings and LlamaCpp
• route based on image content in a multi-modal pipeline
• scale tool selection to thousands of tools without stuffing the context window

When to choose

• you need millisecond routing or tool-use decisions without LLM latency and cost
• you want deterministic, threshold-based fallbacks instead of hallucinated tool calls
• you need local-only execution with no API dependencies
• you want simple route definitions from example utterances

When to avoid

• you need complex multi-step reasoning that requires full LLM generation
• your routing categories need fine-grained classification beyond embedding similarity
• you are not working in Python or an LLM/agent context

Facets

library · maturity active

machine-learning nlp rag agent-framework middleware routing artificial-intelligence large-language-models developer-tools python cross-platform semantic-routing embeddings llm-decision-making guardrails tool-use multi-modal vector-space ai-agents natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="aurelio-labs/semantic-router")