Legit.Show measured Cogni's Security frame at 55/100. Security headers present: HSTS, X-Content-Type-Options. Served over HTTPS with a valid certificate.

How does Legit.Show measure Cogni?

Legit.Show scores seven frames — Performance, Accessibility, Security, Privacy, Reliability, Standards and Discoverability — deterministically from the public surface (URL, HTTP headers, real Lighthouse), with no LLM in the scoring path. See legit.show/methodology.

MCP & Integrations

Cogni

Last updated 2026-08-18 · benchmark measured 2026-09-22 — deterministic & reproducible

Cogni gives AI assistants a persistent, shared memory store via MCP.

87/100

7/7 frames

Top 21% of 14,125 measured · #10 of 57 in ai agent memory

Legit Benchmark — the simple average of 7 measured frames. Frames we could not measure are left out of the average, never counted as zero. Every frame is shown below with its evidence.

Checked 2026-09-22 · scores move as sites change

Are you the maker of Cogni? 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/getcogni-io/2026-09-22. That address never changes; this page moves with every re-measure.

Legit.Show scored Cogni 87/100 on 2026-09-22, measured across all 7 frames from its public surface. legit.show/s/getcogni-io/2026-09-22

Is Cogni production-ready?

Legit.Show scores Cogni 87 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Cogni (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Privacy; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

Performance — 73/100
Accessibility — 90/100
Security — 55/100
How this compares across the catalogue: The Web Security Baseline
Privacy — 100/100
How this compares across the catalogue: The Privacy Gap
Reliability — 100/100
Standards — 92/100
Discoverability — 100/100

What we measured

Security headers present: HSTS, X-Content-Type-Options.
No Content-Security-Policy.
Served over HTTPS with a valid certificate.
Real Lighthouse performance run — 85 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 built it

product account @getcogni_io

Who it's for

Claude users · ChatGPT users · AI agent developers · Power users needing advanced memory · Developers using Cursor, Cline, or other MCP clients

Pricing

Free plan: $0 for personal use; Pro plan: $5/month with 50x limits (50,000 memories)

Sources and updates

Description: Taken from getcogni.io's own website on 2026-08-18.
Operator: Transparent AI, Inc., as named in getcogni.io's terms, privacy page or footer.
Benchmark: Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-09-22.

Put together from public information, without Cogni's involvement. If anything here is wrong, tell us and a person will check it.

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