Claude Skill
RelayPlane/proxy
RelayPlane/proxy is an MIT-licensed open source proxy that cuts AI agent costs by ~80% via smart model routing. Features dashboard, policy engine, and 11 provider support.
Overview
Repository
Install this Skill
npm install -g @relayplane/proxyRegistry
Summary
RelayPlane/proxy is an open-source cost intelligence proxy for AI agents, leveraging smart model routing to cut costs by up to 80%. It features a dashboard, policy engine, and support for 11 providers, all under the MIT license.
面向AI代理的开源成本智能代理。通过智能模型路由削减约80%成本。提供仪表盘、策略引擎，支持11家供应商。采用MIT许可证。
Key features
- Smart model routing to reduce costs by up to 80%
- Built-in dashboard for cost monitoring and insights
- Policy engine for customizable cost management rules
- Support for 11 AI providers including Anthropic and OpenAI
- MIT licensed for open and flexible use
Use cases
- Optimize LLM API costs for AI agent applications
- Centralize cost tracking across multiple AI providers
- Enforce budget policies for enterprise AI deployments
- Route requests to the most cost-effective model automatically
README excerpt
# @relayplane/proxy [](https://www.npmjs.com/package/@relayplane/proxy) [](https://github.com/RelayPlane/proxy/blob/main/LICENSE) A **Node.js npm LLM proxy** that sits between your AI agents and providers. Drop-in replacement for OpenAI and Anthropic base URLs — no Docker, no Python, just `npm install`. Tracks every request, shows where the money goes, and offers configurable task-aware routing — all running **locally, for free**. **Live savings dashboard:** [relayplane.com/live](https://relayplane.com/live) — see real-time aggregate savings from developers worldwide. **The npm-native LLM proxy for Node.js developers.** Works with Claude Code, Cursor, OpenClaw, and any tool that supports `OPENAI_BASE_URL` or `ANTHROPIC_BASE_URL`. **Free, open-source proxy features:** - 📊 Per-request cost tracking across 11 providers - 💰 **Cache-aware cost tracking** - accurately tracks Anthropic prompt caching with cache read savings, creation costs, and true per-request costs - 🔀 Configurable task-aware routing (complexity-based, cascade, model overrides) - 🛡️ Circuit breaker - if the proxy fails, your agent doesn't notice - 📈 **Local dashboard** at `localhost:4100` - cost breakdown, savings analysis, provider health, agent breakdown - 💵 **Budget enforcement** - daily/hourly/per-request spend limits with block, warn, downgrade, or alert actions - 🔍 **Anomaly detection** - catches runaway agent loops, cost spikes, and token explosions in real time - 🔔 **Cost alerts** - threshold alerts at configurable percentages, webhook delivery, alert history - ⬇️ **Auto-downgrade** - automatically switches to cheaper models when budget thresholds are hit - 📦 **Aggressive cache*