AI & Agents
maek
Last updated 2026-07-09 · benchmark measured 2026-11-03 — deterministic & reproducible
maek is a local-first AI assistant that retains memory of your past conversations.
maek at a glance
maek is a local-first AI assistant for macOS that remembers past conversations and organizes them into a searchable map of people, topics, and decisions, aimed at students, writers, researchers, professionals, and language learners.
Good for
- Language learning, where it recalls grammar mistakes you made in earlier sessions and flags repeats
- Worldbuilding and creative writing, where it remembers character details and story facts across a long project
- Work and research notes, where it tracks decisions and next steps agreed on in past conversations
Pricing
Free
Questions people ask
What platforms does maek run on?
maek is currently available for macOS (Apple silicon), with iOS, Android, and Windows versions in development.
Where is my conversation data stored?
Conversations are stored 100% locally on your device by default, with an optional end-to-end encrypted sync; even Cognica, the maker, cannot read your data.
Can I use my own documents with maek?
Yes, you can attach documents and maek answers from the relevant parts, showing citations for where each answer came from.
Which AI models can I use with maek?
You can choose a model that runs locally on your device, or use models from OpenAI or Google.
What are the system requirements for maek on macOS?
It requires Apple silicon, macOS 12 or later, 20GB+ free disk space, and a minimum of 24GB RAM (32GB+ recommended).
Written by Legit.Show from maek.cognica.io on 2026-10-10. It does not change the score.
Are you the maker of maek? 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/maek-cognica-io/2026-11-03. That address never changes; this page moves with every re-measure.
Legit.Show scored maek 77/100 on 2026-11-03, measured across all 7 frames from its public surface. legit.show/s/maek-cognica-io/2026-11-03
Is maek production-ready?
Legit.Show scores maek 77 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on maek (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 70/100
- Accessibility — 96/100
- Security — 45/100How this compares across the catalogue: The Web Security Baseline
- Privacy — 25/100How this compares across the catalogue: The Privacy Gap
- Reliability — 100/100
- Standards — 100/100
- Discoverability — 100/100
What we measured
- Security headers present: HSTS.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 590 ms to first byte.
- Returns a proper 404 for unknown routes.
- 2 of 2 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who it's for
Students · Writers · Researchers · Professionals · Language learners
Pricing
Free
Sources and updates
- Description
- Taken from maek.cognica.io's own website on 2026-07-09.
- 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 2026-11-03.
Put together from public information, without maek's involvement. If anything here is wrong, tell us and a person will check it.
Visit maek → · Alternatives to maek → · How this was measured →
