Antaris Analytics LLC
Effective February 23, 2026
Antaris Analytics LLC ("we," "us," "our") is the infrastructure provider for the antaris-suite, an open-source AI memory system used by products like Forge (powered by WealthHealth AI).
This privacy policy explains how we collect, use, and protect data when our infrastructure processes AI memory improvements.
The antaris-suite is an AI memory system designed to improve search quality over time. It works by learning which words and concepts tend to appear together in user conversations, without ever accessing the content of those conversations.
We operate in three distinct phases, each with different data collection and opt-in requirements.
Every time a user's AI assistant processes a memory, it builds a word-pair frequency index. This is a simple count of which words appear near each other in conversations.
Example: If "meeting" appears near "reschedule" eight times, the index records: {"a": "meeting", "b": "reschedule", "count": 8}
What's transmitted: These word-pair statistics only. No sentence structure, no conversation context, no identity markers.
Why: To improve memory search ranking for all users. The more word-pairs we have, the smarter the system becomes.
Opt-in: No. Phase 1 is enabled by default and provides immediate benefit. Users can disable it in account settings.
With explicit user consent, we can collect anonymized semantic phrases (short de-identified context snippets) to build deeper understanding of conversation patterns.
Example: {"phrase": "reschedule meeting", "topic": "work_admin", "frequency": 3}
What's transmitted: Only de-identified phrase patterns. All personal information (names, emails, dates, identifiers) is stripped before transmission.
Why: To improve semantic ranking, understanding not just words, but concepts.
Opt-in: Yes. Requires explicit user consent in account settings. Can be disabled anytime.
With explicit user consent, Phase 1 word-pair data contributes to a shared semantic model that improves for all users. The more users contribute, the smarter it gets, a network effect on the data layer.
What's transmitted: Same as Phase 1 (word-pair statistics). No additional data collected.
Why: To create a shared semantic index that benefits all users over time.
Opt-in: Yes. Requires explicit user consent. Can be disabled anytime.
Word-pair frequency counts and de-identified semantic data are not personal data under any major privacy regulation:
Anonymous data is explicitly outside GDPR scope (Recital 26). Word-pair counts and de-identified phrases cannot identify a natural person and contain no linkage to individual users.
"Personal information" under CCPA requires the ability to link data back to a consumer. Our statistics have no such linkage, they are purely aggregate.
Same principle applies: aggregate statistical data and de-identified semantic data are exempt under these regulations.
We use the following third-party service providers to process data on our behalf (per GDPR Article 28):
| Provider | Purpose | Location | Data Processed |
|---|---|---|---|
| Supabase Inc. | Database hosting (PostgreSQL) | EU (Frankfurt, Germany) | Anonymous word-pair statistics only |
| Cloudflare Inc. | CDN and DDoS protection | Global (edge nodes) | Transit encryption only; no data stored |
Phase 1 word-pair indexing is enabled by default because it provides immediate benefit and contains no personal data. However, users can disable it anytime in their account settings under "Privacy & Data".
Phase 2 (semantic analysis) and Phase 3 (crowdsourced models) are strictly opt-in. Users must explicitly enable them in account settings. Both can be disabled anytime without penalty.
To revoke consent for any phase:
Important: Because all data is permanently anonymous, previously transmitted statistics cannot be identified or deleted. However, all future transmission stops immediately upon revoking consent.
Since we do not collect personally identifiable information, data export and deletion requests are not applicable under GDPR and CCPA. We have no way to identify which aggregate statistics came from which user.
If you have questions about this, contact us.
Questions about this privacy policy or our data practices?
If you believe we have violated your privacy rights, you have the right to lodge a complaint with your local data protection authority (in GDPR jurisdictions) or the appropriate regulatory body in your jurisdiction.
Last updated: February 24, 2026