Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.

A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and +1.9 pts completion on our tested dataset.

Reduce your LLM costs by 40-70% automatically. Routes prompts locally, compacts context, tracks real savings.

Local, zero-token intent routing for chat, tooling, coding, and planning prompts.

Route every prompt to the best LLM — for you specifically.

Host-aware model routing for coding agents. Python library + MCP server for Claude Code, Codex, Gemini CLI, Copilot, Cursor, and Aider.

Blazing-fast, zero-cost local LLM router. Classify and route prompts to specialized AI models with <1ms latency using heuristic rules.

Intelligent multi-model LLM routing gateway — route each request to the optimal model, save 40-70% on API costs. Single binary, OpenAI-compatible.

Make OpenCode spend ~90% less on tokens: smart routing sends easy work to Flash, hard work to flagships. 22 agents, one-command deploy（一键部署）

Route prompts to local large language models instantly to cut costs and reduce latency with smart, zero-overhead classification under 1 millisecond.

Energy-efficient AI prompt routing system — sends simple prompts to lightweight models and reserves larger models for complex reasoning to cut compute, latency, and energy.

Run a team of AI coding agents (Claude Code, Codex, Gemini, Hermes) side by side in tmux, with a YAML-defined ACL. Zero dependencies.

The control plane for Claude Code. Run a dozen MCP servers and a hundred skills. Pay context for only the ones doing work right now.

Local prompt routing studio for structured AI workflows and execution handoff.

Intelligent LLM request router for Azure OpenAI — automatically routes prompts to GPT-4o-mini or GPT-4o based on complexity, task type, environment, and budget. Cuts AI API costs by 60-80% with zero impact on application quality.

OpenAI-compatible LLM gateway that routes each prompt to the cheapest qualified model — local Ollama first, cloud only when needed.

Intelligent LLM router that dynamically routes prompts between local Ollama (Qwen) and cloud models (Gemini) using complexity scoring, semantic caching, and cost-aware decisioning.

Prompt posture router for coding tasks; pairs with causetrace

MCP server that intelligently routes prompts across Claude, Gemini, and GPT-4o based on task type — minimising token cost without sacrificing quality.