semantic-routing

Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15 specialized tools, function pipelines, and filters, this project supports academic research, agentic autonomy, multimodal creativity, workflows, and more

Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.

Low latency, High Accuracy, Custom Query routers for Humans and Agents. Built by Prithivi Da

Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load balancing across OpenAI, Anthropic, Ollama, vLLM, and any compatible backend. Identity-based access, virtual API keys, and end-to-end encryption via OpenZiti

Redis Vector Library (RedisVL) -- the AI-native Java client for Redis.

A flexible and easy to use tool for Semantic Routing

A self-hosted knowledge broker for homelabs. Routes and fuses queries across Kiwix, FreshRSS, Open-Meteo, SearXNG, Uptime Kuma, and Home Assistant — and tracks what changed over time. REST API and MCP server, integrates natively with Open WebUI and Home Assistant.

Single-forward-pass semantic routing in Rust: turn dense LLMs (Llama, Qwen, Mistral, Gemma) into a typed decision API with LoRA/QLoRA training and FP8/FP4 quantization, built on Candle.

A comprehensive AI companion leveraging advanced semantic analysis, sentiment detection, and voice processing to provide personalized and context-aware interactions using Autogen, semantic-router, and VoiceProcessingToolkit.

A magical witch assistant equipped with an enchanted grimoire powered by AI, yet shaped by you: your agents, prompts and tools...woven into her spells. Built with ❤️ using .NET 10, Akka.NET and Microsoft Agent Framework.

Sentinel-Triage is a content moderation system that uses semantic routing to classify user-generated content and route it to the optimal AI model based on intent, risk level, and language.

🚀 MCP Gateway with Semantic Routing — One API for all your MCP tools. Natural language in → right tool executed. Blazing fast (Cerebras) + always reliable (multi-LLM fallback).

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.

Open-source local-first AI assistant runtime with graph memory, semantic tool routing, markdown-governed tools, FastAPI/Next.js frontend surfaces, and verified tool calling.

A high-performance request router for vLLM — smart load balancing, response caching, prefill/decode disaggregation, semantic routing, Anthropic/OpenAI API translation, and operational tooling out of the box.

Training-free decision engine for existing MLX models on Apple Silicon. No fine-tuning or extra decision weights. MLX-LM + experimental MLX-VLM action selection and semantic routing. Related: AnyJev.

Picks the option that fits a text, or says none does. Intent and ticket routing on CPU, 25 languages, no API.

An Agentic Workflow built with LangGraph and LangChain that implements AI Orchestration via Conditional State Graphs, using Semantic Routing and Persistent Memory to deterministically triage user queries

Routes each prompt to the right model by difficulty. OpenAI/Anthropic-compatible API, MCP server, and a chat demo included.

A TypeScript library that answers a decision question with a probability distribution over every option, using any existing LLM