# aurelio-labs/semantic-router

Superfast AI decision making and intelligent processing of multi-modal data.

Repository: https://github.com/aurelio-labs/semantic-router
Canonical: https://ross.abutalabs.com/products/aurelio-labs-semantic-router
Homepage: https://www.aurelio.ai/semantic-router
Language: Python
License: MIT
License Family: permissive
Topics: ai, artificial-intelligence, chatbot, computer-vision, generative-ai, machine-learning, nlp
Last push: 2026-08-24T20:46:59+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 74
- inputs: {"age_days": 1038, "days_push": 9, "days_rel": 9, "gap_med": 9, "n_releases_24m": 26}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3841, forks 365 (observed 2026-08-28T04:08:23.962063+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, nlp, rag, agent-framework, middleware, routing
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: semantic-routing, embeddings, llm-decision-making, guardrails, tool-use, multi-modal, vector-space, ai-agents, natural-language-processing

## Member repositories
- aurelio-labs/semantic-router (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:23.962063+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:26:13.650340+00:00, confidence not recorded.
  - readme: https://github.com/aurelio-labs/semantic-router (fetched 2026-08-28T04:08:23.962063+00:00, sha b0a3257042bc)
  - homepage: https://www.aurelio.ai/semantic-router (fetched 2026-08-29T09:20:54.904609+00:00, sha c9366d546b73)
  - site_page: https://docs.aurelio.ai/semantic-router/get-started/introduction (fetched 2026-08-29T09:20:54.907149+00:00, sha fe46c8b8db5c)
- Data as of 2026-08-30T08:39:29.467469+00:00.