An open, programmable decision layer for models and compute.
LLM Semantic Router: Intelligent Mixture-of-Models (MoM) System with Privacy Preservation and Prompt Guard. The semantic router intelligently directs OpenAI compliant API requests to the most suitable backend models based on semantic understanding of request content.
AI coding assistant rule manager for Claude Code, Cursor, and Codex. Load only the rules you need.
GenPark AI Agent Skill - Dynamic agent skill registry with semantic capability embeddings, signature match scoring, and Jaccard keyword routing.
GenPark AI Agent Skill - Dynamic agent skill registry with semantic capability embeddings, signature match scoring, and Jaccard keyword routing.
🏆 First prize, Superlinked × Qwen Hackathon 2026 — a training-free, self-improving semantic router: kNN over an exemplar index, LLM-judge writeback, 75%→85% in one day at half the cost
Universal Agent Skill Router — Route agent skills before LLM inference. Zero-config skill fingerprinting, conflict-aware routing, and self-learning feedback loop. Supports OpenClaw, Claude Code, LangChain, and more.
Explore the integration of semantic routing with graph-based configurations using Semantic Router and LangGraph. This project demonstrates advanced routing techniques for applications in chatbots, text classification, and NLP, providing a robust framework for developers.
Semantic-Router-C-Sharp is a superfast decision-making layer for your LLMs (Large Language Models) and agents in C#. Instead of relying on slow LLM generations to make tool-use decisions, this router uses the power of semantic vector space to make fast decisions by routing requests based on semantic meaning.
Route predictable natural-language requests to deterministic workflows without using a generative LLM for the routing decision.
Federated RAG that picks the right store with arithmetic, not an agent. Runs locally based on Vulkan.
Identify and protect personal data in text by intercepting and masking PII using Java middleware for enhanced data privacy compliance.
Multilingual decision engine for intents you describe in plain words, no training examples. It picks the matching intent, with a margin that flags doubtful answers; R2Intent v1 also answers yes or no (beta), with probabilities. About 26 ms per message on a GPU (compiled). Python, HTTP or MCP, self-hosted. Library Apache-2.0; models CC BY-NC 4.0.
Smart LLM routing — classifies queries by complexity and routes to the right model. Exposes cost and latency telemetry.
Letitbe Router: semantic routing plus adaptive limit-aware scheduling for AI agents and models
FastAPI-based multi-agent orchestrator for Odoo. Uses a Semantic Router to dispatch intents to specialized agents via Model Context Protocol (MCP/FastMCP). Features Guardrails AI for hallucination prevention, Human-in-the-Loop validation, Logfire observability and support for Groq, Ollama and vLLM.
ShoppingGPT is a production-ready, agentic AI chatbot for e-commerce. It routes every conversation through a semantic classifier, dispatches to specialized LangChain tools, and streams back intelligent responses — all in under a second.
Zero-shot intent classification and out-of-scope detection. 150M model, 94.9% routing accuracy. ONNX int8 on CPU (160 ms p95) or MLX on Apple Silicon (~15-25 ms). Distilled from Laya into Ettin-150M.
Capability-aware inference gateway deployment for Kubernetes, Docker Compose and external model hosts, powered by Envoy and native Semantic Router.
To associate your repository with the semantic-router topic, visit your repo's landing page and select "manage topics."