Find tools › Open-source projects › Spend less on AI

rtk

Open-source project · by rtk-ai

A small helper that trims long terminal output before your AI coding tool reads it, so you pay for less text.

Some setupVery popular

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Cut the text your AI agent reads from test runs
  • Stretch your AI coding plan's limits further
  • Keep long command output from crowding the AI's memory

How to start

  1. Install it with Homebrew on Mac, winget on Windows, or the install script in the README.

  2. In a terminal, run rtk init -g to hook it into your AI coding tool.

  3. Keep working as usual; savings apply to command output, not your whole AI bill.

Good to know. The repository claims up to 90% bash output reduction, but this refers strictly to shell output size, not your total API bill. Token counts are approximated using bytes/4 rather than a precise tokenizer.

Before you install

  • Checked by a personWe read what it does before listing it.
  • License: Apache-2.0You are allowed to use it under these terms.
  • Last updated 2026-11-18

More detail

High-performance CLI proxy that intercepts and compresses shell command outputs before they reach your coding agent's context window.

Coding agents often spew thousands of lines of raw terminal output from commands like git status, test suites, and file reads into the LLM context. Reach for RTK to dramatically slash bash output volume, reduce token waste, and speed up agent workflows.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map