🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Desktop proxy for AI subscriptions in coding tools
ProxyPal sits between your AI accounts and your coding tool, using CLIProxyAPI under the hood. You connect accounts in the app, start the local proxy, and then point Cursor, Claude Code, or another client at the local endpoint.
Builders who want one local proxy for Claude, ChatGPT, Gemini, and Copilot across different coding tools.
You can use your AI subscriptions in the client you already prefer while keeping usage and requests in one dashboard.
What it does
Multiple AI provider connections
Connect Claude, ChatGPT, Gemini, Qwen, iFlow, Vertex AI, and custom OpenAI-compatible endpoints.
GitHub Copilot bridge
Use Copilot models through an OpenAI-compatible API.
Antigravity support
Route thinking models through an Antigravity proxy.
Works with many clients
Supports Cursor, Claude Code, OpenCode, Cline, Continue, GitHub Copilot, and other OpenAI-compatible tools.
Usage analytics
Tracks requests, tokens, success rates, and estimated savings.
Request monitoring
Shows API requests with response times and status codes.
Auto-configuration
Detects installed CLI agents and sets them up automatically.
How to get it
- 1The app is not signed with an Apple Developer certificate yet. If macOS blocks the app
xattr -cr /Applications/ProxyPal.app
README
ProxyPal
Use your AI subscriptions (Claude, ChatGPT, Gemini, GitHub Copilot) with any coding tool. Native desktop app wrapping CLIProxyAPI.

Why ProxyPal?
You're paying for Claude, ChatGPT, or GitHub Copilot. Why can't you use them in your favorite coding tool?
ProxyPal bridges that gap. One proxy, all your AI subscriptions, any client.
Features
- Multiple AI Providers - Connect Claude, ChatGPT, Gemini, Qwen, iFlow, Vertex AI, and custom OpenAI-compatible endpoints
- GitHub Copilot Bridge - Use Copilot models via OpenAI-compatible API
- Antigravity Support - Access thinking models through Antigravity proxy
- Works Everywhere - Cursor, Cline, Continue, Claude Code, OpenCode, and any OpenAI-compatible client
- Usage Analytics - Track requests, tokens, success rates, and estimated savings
- Request Monitoring - View all API requests with response times and status codes
- Auto-Configure - Detects installed CLI agents and sets them up automatically
Quick Start
- Download from Releases
- Launch ProxyPal and start the proxy
- Connect your AI accounts (OAuth or auth files)
- Point your coding tool to
http://localhost:8317/v1
macOS Users
The app is not signed with an Apple Developer certificate yet. If macOS blocks the app:
xattr -cr /Applications/ProxyPal.app
Supported Platforms
| Platform | Architecture | Status |
|---|---|---|
| macOS | Apple Silicon (ARM64) | ✅ |
| macOS | Intel (x64) | ✅ |
| Windows | x64 | ✅ |
| Linux | x64 (.deb) | ✅ |
Supported Clients
Works with Cursor, Claude Code, OpenCode, Cline, Continue, GitHub Copilot, and any OpenAI-compatible client.
Development
pnpm install
pnpm tauri dev
Checks
pnpm check:ts # tsgo when installed, otherwise tsc --noEmit
pnpm check:parallel # check:ts + lint + format:check (parallel)
cd src-tauri && cargo check
Optional tsgo setup:
pnpm add -D @typescript/native-preview
Optional VS Code setting:
{
"typescript.experimental.useTsgo": true
}
Tech Stack: SolidJS + TypeScript + Tailwind (frontend), Rust + Tauri v2 (backend), CLIProxyAPI (proxy)
Contributing
- One feature per PR - Keep changes focused
- Clean commits - No unrelated changes
- Test your changes - Run
pnpm tauri devand verify - Follow existing patterns - Check similar implementations
Adding a New Agent
- Add detection logic in
src-tauri/src/lib.rs - Add logo to
public/logos/(usecurrentColorfor dark mode) - Update agents array in relevant components
- Test auto-configuration flow
Support
If ProxyPal saves you time, consider buying me a coffee.
License
MIT
Star History
Files in the repo
- .github
- .pi
- cli-proxy-api-management
- docs
- public
- scripts
- src
- src-tauri
- .env.example
- .fallowrc.json
- .gitignore
- .ignore
- .npmrc
- .oxfmtrc.jsonc
- AGENTS.md
- bun.lock
- index.html
- LICENSE
- oxlint.config.mjs
- package.json
- pnpm-lock.yaml
- postcss.config.js
- README.md
- RELEASE_NOTES.md
- tailwind.config.js
- TEST_PLAN.md
- tsconfig.json
- tsconfig.node.json
- vite.config.ts
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More tools
The best-benchmarked open-source AI memory system. And it's free.
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.

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.