Introduction

Harness

Harness is an AI that sits next to you and sees what you see. It lives in a small window that stays with you while you work, looks at the same screen you are looking at, remembers what matters to you, and thinks alongside you. Not a chat box in another tab. A sharp, private second pair of eyes on your actual work.

It runs local-first: your screen understanding and your memory live on your own machine by default, and they do not leave it to make Harness work. Your AI, your machine.

Why it is different

  • It sees your screen. Ask about what is in front of you and get an answer grounded in the pixels that are actually there, not a guess from a description you had to type. It also keeps a private timeline of your screen, so you can ask what you were looking at an hour or a day ago.
  • It remembers you. Harness builds a private, on-device model of your preferences, your work, and your corrections, and gets sharper about you the longer you use it.
  • It is private by construction. The models that read your screen run in your browser. The memory of what it has learned lives on your device. Nothing about your screen is shipped anywhere for Harness to work.
  • The AI is yours to choose. Run a model locally, bring your own Venice or Bankr key, or use managed inference and pay as you go. Every account starts with $5 of managed inference, free.

Running Harness

  • Hosted. Sign in at tryharness.ai and you are working in seconds.
  • Self-hosting. Running the full stack yourself is planned, not yet available. See Self-hosting to follow along.

Start here

Getting started