Built for AI Agents — Claude Code, Cursor, and more

Cut Your LLM Token
Costs by 30–70%

T-Lang compresses your prompts server-side before they hit the LLM. Your AI agent sets it up in 2 commands. You just click login once.

Quick Start

Tell your AI agent to run these commands. You only need to click the login link once.

1Agent authorizes CLI — opens a link, you click login
npx tlang-cli auth login
# → Opens: https://tlang-eu5.pages.dev/auth/device?code=ABC123
# → You log in once → CLI auto-receives your key
2Agent adds your LLM provider key
npx tlang-cli provider add openai --key sk-your-key
# Built-in: openai | gemini | grok | deepseek | groq
Done! Every call is now auto-compressed
npx tlang-cli chat "Summarize this article about quantum computing" --model gpt-4o-mini

# Output (JSON):
# {
#   "content": "Quantum computing uses qubits...",
#   "compression": { "original_tokens": 45, "compressed_tokens": 12, "saved_tokens": 33, "rate": "73.3%" }
# }
#
# stderr: T-Lang: 45 -> 12 tokens (saved 33, -73.3%)

How It Works

Compression stays on the server. Your API keys stay on your machine.

CLI on Your Machine

Sends prompts to T-Lang Worker for compression. Zero dependencies — Node.js 18+ only.

T-Lang Worker

Compresses your prompt using T-Lang DSL. Returns compressed messages. Never sees your Provider key.

Direct to Provider

CLI calls OpenAI/Gemini/Grok directly with your local key. Fewer tokens = lower bill.

Compression Example

Original (18 tokens)
"Please summarize the following article, keeping it under 100 words as a bullet list"
Compressed (4 tokens)
!Sum [article] ?Len<100 ?Fmt:List
78% token savings — LLM understands both equally well

Why T-Lang?

Keys Never Leave Your Machine

T-Lang only compresses your prompt. Your OpenAI/Gemini/Grok API key goes directly from your CLI to the provider. We never see it.

Agent-Native Setup

Designed for AI coding agents. Two commands to install. One browser click to authorize. Your agent handles the rest.

Smart Compression

Automatically skips code blocks, short messages, and system prompts. Zero quality loss on supported patterns.

Pricing

Start free. Upgrade when it pays for itself.

Free

$0

No credit card required

  • 20 compressions per day
  • All providers (OpenAI, Gemini, Grok, DeepSeek, Groq)
  • Usage dashboard
  • Graceful fallback when limit reached
Get Started
Recommended

Pro

$19/month

Pays for itself after ~$25 in API savings

  • Unlimited compressions
  • All providers
  • Priority compression engine updates
  • Email support
Upgrade to Pro

Free tier exceeds daily limit? Your API calls still work — just without compression savings.

Tell Your Agent to Get Started

npx tlang-cli auth login

Create Free Account