AI & Agents

Hunch

Last updated 2026-08-25 · benchmark measured 2026-08-25 — deterministic & reproducible

Hunch is a free, open-source AI computer-use agent for macOS that runs tasks in the background.

Is Hunch production-ready?

Legit.Show scores Hunch 76 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Hunch (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 75/100
• Accessibility — 91/100
• Security — 45/100
• Privacy — 70/100
• Reliability — 100/100
• Standards — 89/100
• Discoverability — 60/100

What we measured

• Security headers present: HSTS.
• No Content-Security-Policy.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 146 ms to first byte.
• Returns a proper 404 for unknown routes.
• 3 of 3 sampled routes reachable.
• Has a reachable privacy policy.
• Sets cookies / loads scripts with no consent prompt.

Who it's for

macOS users · developers · productivity-focused professionals · students · technical users

Pricing

Free (requires existing Claude or ChatGPT/Codex subscription)

Visit Hunch → · Alternatives to Hunch → · How this was measured →