Google PageRank for AI agents. 25,000+ tools indexed.

proxy MCP Server

RelayPlane/proxy

Score: 67.8 Rank #4513 Monitoring
[![AgentRank](https://agentrank-ai.com/api/v1/badge/RelayPlane--proxy)](https://agentrank-ai.com/tool/RelayPlane--proxy/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of RelayPlane/proxy? Claim this listing →

Local-first LLM proxy that meters what every agent run costs and kills runaways before they drain your budget. Free, MIT.

Add AgentRank to Claude Code Discover and compare tools like RelayPlane/proxy — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

RelayPlane/proxy is a TypeScript tool licensed under MIT. Local-first LLM proxy that meters what every agent run costs and kills runaways before they drain your budget. Free, MIT. Topics: agent-cost, claude-code, cost-attribution, llm-gateway, llm-proxy, local-first, mcp, observability, open-source.

Ranked #4513 out of 24846 indexed tools.

Ecosystem

TypeScript MIT
agent-costclaude-codecost-attributionllm-gatewayllm-proxylocal-firstmcpobservabilityopen-source

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 207

207 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 38%

3/8 issues closed → many open issues

Contributors 10% 4

4 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 33
Description Good
License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Freshness high impact

Last commit was 41 days ago — a recent commit would boost your freshness score

Issue Health high impact

You have 5 open vs 3 closed issues — triaging stale issues improves health

Badge all embed codes →

AgentRank score for RelayPlane/proxy
[![AgentRank](https://agentrank-ai.com/api/v1/badge/RelayPlane--proxy)](https://agentrank-ai.com/tool/RelayPlane--proxy/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/RelayPlane--proxy/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/RelayPlane--proxy" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="RelayPlane/proxy"></script>

Matched Queries

topic:mcp

From the README

# RelayPlane

**Know what every agent run costs. Kill the runaway before it drains your budget.**

A local proxy that sits between your AI agents and their model providers,
prices every request as it happens, rolls the cost up per run and per agent,
and lets you cap or kill spend before a loop turns into a bill.

RelayPlane runs on your machine and is a drop-in replacement for the Anthropic
and OpenAI base URLs: no Docker, no Python, no account, and nothing leaves your
machine unless you turn it on. It is for people running multi-agent or fan-out
workloads who cannot tell which run ate the bill. MIT licensed, no paid tiers,
the whole product is in this repo.

## Quick start (30 seconds)

```bash
npm install -g @relayplane/proxy
relayplane start
```

Point Claude Code (or any tool that speaks the Anthropic or OpenAI API) at it:

```bash
export ANTHROPIC_BASE_URL=http://localhost:4100
claude
```

That is the whole setup. Open http://localhost:4100 for the live dashboard, or
run `relaypla
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.