Plano is an AI-native proxy and data plane for agentic apps — with built-in orchestration, safety, observability, and smart LLM routing so you stay focused on your agents core logic.

A curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble"

High-performance lightweight proxy and load balancer for LLM infrastructure. Intelligent routing, automatic failover and unified model discovery across local and remote inference backends.

RouterArena: An open framework for evaluating LLM routers with standardized datasets, metrics, an automated framework, and a live leaderboard.

Your agents silently degrade in production. Kalibr keeps them on the optimal path — scoring every call, learning what works, routing automatically.

Execution-governance layer for hybrid AI systems: route requests across local, private, and public models safely, cost-effectively, and auditably.

Edge-native AI API gateway — cost-optimized routing across providers, multi-protocol support, built on Cloudflare Workers.

Intelligent model routing for OpenClaw with quota prediction, task classification, and automatic optimization

3-Tier hybrid AI router that orchestrates FunctionGemma-270M on-device and Gemini 2.5 Flash Lite in the cloud for 99% function-calling accuracy at 548ms avg latency. Built at the Cactus × Google DeepMind Hackathon.

MCP AI Bridge — smart multi-model routing for Antigravity. Route tasks to the best AI model automatically.

Production-ready AI Agent Template optimized for Azure

Compose, train and test fast LLM routers

An applied AI system using LLM routing, hybrid retrieval, and structured positive/negative reasoning for decision support.

Unified interface server for various LLM providers with OpenAI API format

Hybrid AI routing: LOCAL Ollama + CLOUD GitHub Copilot

A neural multi-armed bandit framework for routing prompts to the most suitable LLM in a multi-agent system.

Provider-agnostic MCP control plane for managing connections, routing requests, and policy enforcement across AI vendors.

🧠 Smart AI chatbot that automatically routes queries to the optimal LLM based on complexity — saving up to 75% on API costs. Simple questions go to free local models (Ollama), while complex ones route to GPT-4o. Built with Next.js, TypeScript, and Turborepo.

NeurIPS 2025 paper "MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees"

P402 Payment Protocol