If you use a coding agent like Cursor or Windsurf every day, you've probably noticed two things:

  1. Your token usage is massive — every file context, conversation history, and tool output gets sent to the LLM as prompt tokens
  2. Your bill grows with it — at GPT-4 Turbo pricing ($10/1M input tokens), a heavy Cursor user spends $50–200+/month on prompt tokens alone

We built SuperCompress to solve this: it compresses prompt context before it reaches the LLM, cutting token costs by ~65% with no quality loss. The problem was always integration — adding middleware, configuring agents, setting up proxies. Too many steps.

Not anymore.

One Command

# Install once. Run setup once. It's forever. npm install -g @supercompress/proxy supercompress setup

That's it. The setup command walks you through getting an API key, then automatically:

  1. Detects every coding agent installed on your machine
  2. Configures each one to point at the local proxy
  3. Registers the proxy as a background service (auto-starts on login)

From this moment forward, every single LLM call from every single coding agent is compressed. You never think about it again.

Works With Every Agent

✓ Cursor
✓ Windsurf
✓ Continue
✓ Cline
✓ Claude Code
✓ Aider

New coding agent comes out next week? supercompress setup again and it's wired up. That's the beauty of the proxy approach — one codebase, zero plugins, every agent.

How It Works

The proxy runs on your machine at localhost:8080. Your coding agents are configured to send their LLM requests there instead of directly to OpenAI/Anthropic. The proxy:

  1. Receives the messages from your coding agent
  2. Compresses the context using the SuperCompress API (billable through your plan)
  3. Forwards the compressed messages to the real provider (OpenAI/Anthropic)
  4. Returns the response back to your coding agent

Your provider API key stays on your machine. Only the context text is sent to the SuperCompress API for compression. The proxy adds ~60ms of overhead — invisible compared to a 5–30 second LLM call.

The Cost Math

Metric Without Proxy With Proxy
Tokens per request ~4,000 ~1,400
Cost per 1K requests (GPT-4 Turbo) $40 ~$14
Monthly cost (heavy Cursor user) $50–200 ~$18–70
Context window fit 100K window fills fast ~3x more effective space

What About SuperCompress Pricing?

Every compression call goes through the SuperCompress API, which counts against your plan's monthly token quota. Here's what that means:

Plan Price Tokens/Month With a Coding Agent
Free $0 100K 1–2 days of Cursor → upgrade
Starter $10/mo 5M 1–2 months for light users
Pro $20/mo 15M The sweet spot for daily devs
Business $60/mo Unlimited Teams, shared proxy

The math works in your favor. If you're spending $50–200/month on Cursor tokens, saving 65% means you save $33–130/month. The Pro plan costs $20. You come out ahead by $13–110/month. The more you use Cursor, the more you save.

For Teams

Run the proxy as a shared Docker container for your whole team:

docker run -p 8080:8080 \
  -e SUPERCOMPRESS_API_KEY=sc_live_team_key \
  -e PROXY_PORT=8080 \
  supercompress/proxy

Every developer on the team configures their agent to point at the shared proxy. Usage is centralized under one Business plan ($60/mo, unlimited tokens). The dashboard shows per-developer usage.

What Developers Are Saying

"I was spending $180/month on Cursor. After installing the SuperCompress proxy, it dropped to ~$60/month. The setup took 30 seconds and I haven't touched it since."

"The auto-detection found all three of my agents (Cursor, Continue, Claude Code) and configured them all at once. This is how every developer tool should work."

Get Started

# One time. Forever. npm install -g @supercompress/proxy supercompress setup

You'll need a SuperCompress API key. If you don't have one, the setup command will point you to supercompress.dev/dashboard to create a free account.

For complete documentation, check the API docs. For the source code, visit GitLab.