AI & Agents
Mercury Agent
Source: cosmicstack-labs/mercury-agent · ★ 2992 · TypeScript
Last updated 2026-08-06 · benchmark measured 2026-08-22 — deterministic & reproducible
An AI terminal agent that thinks, acts, and asks permission before making changes.
Are you the maker of Mercury Agent? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/gh-cosmicstack-labs-mercury-agent/2026-08-22. That address never changes; this page moves with every re-measure.
Legit.Show scored Mercury Agent 59/100 on 2026-08-22, measured across all 7 frames from its public surface. legit.show/s/gh-cosmicstack-labs-mercury-agent/2026-08-22
Is Mercury Agent production-ready?
Legit.Show scores Mercury Agent 59 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Mercury Agent (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Accessibility; its weakest is Discoverability. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 87/100
- Accessibility — 92/100
- Security — 25/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 25/100How this compares across the catalogue: The Privacy Gap
- Reliability — 92/100
- Standards — 70/100
- Discoverability — 25/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 176 ms to first byte.
- Returns a proper 404 for unknown routes.
- 0 of 0 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
- Discoverable: sitemap.
Who it's for
developers · teams · automation enthusiasts · terminal users · organization admins
Visit Mercury Agent → · Alternatives to Mercury Agent → · How this was measured →