Plain-AyI
← All projects
Add-ons for AI coding tools

Headroom

Shrinks the text an AI assistant has to read, so it uses fewer tokens and costs less.

Fast-rising

What it does

AI models are billed by "tokens", small chunks of text. AI coding assistants often read long logs, files and tool results, which uses many tokens. Headroom squeezes that material down before it reaches the AI model.

Its makers say the answers stay the same while the text gets much shorter. The compression runs on your own computer, and the original text is kept so the AI can ask for the full version if it needs it.

You can wrap a coding tool such as Claude Code, Codex, Cursor or Aider with one command, run it as a proxy (a middle step that passes messages along), use it as a code library, or connect it as an MCP server, a standard way to plug tools into AI assistants.

Who it's for

Developers who use AI coding assistants or build AI apps and want to cut token use and costs.

Can I use it without coding?

Developers only. It's installed and run from the command line or added to code. New to this? Start here.

Can I run it?

Cost
Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
Privacy
Sends what you give it to an online service
API key
Not needed

Try it

  1. Install the Headroom command-line tool on your computer.
  2. Use Headroom's wrap option to start your AI coding agent through it.
  3. Open the Headroom dashboard to see how many tokens you are saving.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • What you type or upload is sent to an online service. Avoid sharing private or sensitive information.
  • More on staying safe

Where people are talking about it