Skip to content

Cc Gateway

AI API identity gateway — reverse proxy that normalizes device fingerprints and telemetry for privacy-preserving API proxying

Install

$git clone https://github.com/motiful/cc-gateway

Install command taken from the project's README or registry entry. Always review code before running it.

Take back control of your AI API telemetry

Quick Start · Add Clients · What Gets Rewritten · Deployment · Changelog


Alpha — This project is under active development. Test with a non-primary account first.

Disclaimer — See full disclaimer below.

Why

Claude Code collects 640+ telemetry event types across 3 parallel channels, fingerprints your machine with 40+ environment dimensions, and phones home every 5 seconds. Your device ID, email, OS version, installed runtimes, shell type, CPU architecture, and physical RAM are all reported to the vendor — continuously.

If you run Claude Code on multiple machines, each device gets a unique permanent identifier. There is no built-in way to manage how your identity is presented to the API.

CC Gateway is a reverse proxy that sits between Claude Code and the Anthropic API. It normalizes device identity, environment fingerprints, and process metrics to a single canonical profile — giving you control over what telemetry leaves your network.

Features

  • Full identity rewrite — device ID, email, session metadata, and the user_id JSON blob in every API request are normalized to one canonical identity
  • 40+ environment dimensions replaced — platform, architecture, Node.js version, terminal, package managers, runtimes, CI flags, deployment environment — the entire env object is swapped, not patched
  • System prompt sanitization — the <env> block injected into every prompt (Platform, Shell, OS Version, working directory) is rewritten to match the canonical profile
  • Billing header stripped — the x-anthropic-billing-header (which contains a per-session fingerprint hash) is removed entirely, consistent with the official CLAUDE_CODE_ATTRIBUTION_HEADER=false toggle. This also enables cross-session prompt cache sharing, reducing system prompt costs by ~85%
  • Process metrics normalization — physical RAM (constrainedMemory), heap size, and RSS are masked to canonical values so hardware differences don't leak
  • Zero-login client setup — clients receive a single launcher script. No browser OAuth, no ~/.zshrc changes, no config files
  • Centralized OAuth — the gateway manages token refresh internally; client machines never contact platform.claude.com
  • Instant startup — gateway uses your existing access token on launch. No network call until the token actually expires
  • Proxy-aware — supports HTTPS_PROXY / HTTP_PROXY env vars for outbound connections (Clash, V2Ray, etc.)
  • Telemetry leak prevention — strips baseUrl and gateway fields that would reveal proxy usage in analytics events

Quick Start

One command. Requires Node.js 22+ and an existing Claude Code login on this machine.

git clone https://github.com/motiful/cc-gateway.git
cd cc-gateway
npm install
bash scripts/quick-setup.sh

This will:

  1. Extract your OAuth credentials from macOS Keychain (access token + refresh token)
  2. Generate a canonical device identity and client token
  3. Write config.yaml
  4. Generate a client launcher at ./clients/cc-<hostname>
  5. Start the gateway on http://localhost:8443

Use it

In another terminal:

./clients/cc-<hostname>

That's it. Claude Code launches, traffic routes through the gateway. No env vars to set, no files to edit.

Behind a proxy?

Similar plugs

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro,…

Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Devin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini…