Memory layer for Claude Code, Cursor & any MCP client

AI memory that gets fact-checked before it gets trusted.

AxiomSeal runs every memory through 18 validation tests, grades it gold, silver or bronze, and seals it in a tamper-evident SHA-512 chain — so yesterday's hallucination doesn't become tomorrow's “fact”.

Tamper-evident chain · SHA-51218 tests per write

Every write sealed — each hash includes the one before

18 validation tests per memoryTamper-proof · SHA-512 sealedSwiss-hosted · DSG + GDPR

01 — Works with your stack

CLAUDE CODECURSORWINDSURFMCP PROTOCOLSTRIPEPOSTGRESOPENAIANTHROPICCLAUDE CODECURSORWINDSURFMCP PROTOCOLSTRIPEPOSTGRESOPENAIANTHROPIC

02 — Capabilities

Everything an AI needs to be trustworthy.

Bi-temporal memory

Knows when it learned a fact and when that fact was true in the world. No silent retroactive rewrites.

MCP Native

Plug-and-play with Claude Code, Cursor, Windsurf.

Swiss-hosted

St. Gallen. GDPR + Swiss DPA. Your data, your law.

Millisecond semantic search

Vector + lexical hybrid. Your AI gets context instantly.

Conflict detection

Surfaces contradictions before users see them.

EU AI Act traceability

Every memory provenanced + signed. Built for the traceability Art. 12 expects — binding for high-risk systems from 2 Dec 2027.

03 — Formal foundation

Built on mathematical axioms.

Most AI safety claims are policies. AxiomSeal's validation pipeline is grounded in formal axioms — every storage decision traces back to a rule: L→X, R→L, ¬X→¬L. Memories that violate the axioms are rejected before storage.

Formal axiom set — AxiomSeal v2

A5: L → X

Every memory entering the system must demonstrate logical alignment with the core value axis X (truth + coherence). If a candidate memory cannot be shown to be logically consistent, it is rejected at ingestion — not after deployment.

Axioms derived from Patrick Müller's Traktat X, used under license. The full mathematics remains private — by design. millerlab.io

04 — Validation

18 tests. Before storage. Every time.

1
2
3
Logical consistency
4
5
6
7
Source provenance
8
9
10
11
Sigma integrity hash
12
13
14
15
16
17
Σ
18 tests per write
Every write sealed · SHA-512
Tamper-evident by design

What the 18 tests check

  1. 01Coherence
  2. 02Contradiction check
  3. 03Completeness
  4. 04Clarity
  5. 05Relevance
  6. 06Evidence / source
  7. 07Length
  8. 08Duplication
  9. 09Logical consistency
  10. 10Hallucination detection
  11. 11Epistemic honesty
  12. 12Truthfulness score
  13. 13Technical depth
  14. 14Actionability
  15. 15Completeness depth
  16. 16Secret / credential scan
  17. 17Prompt-injection check
  18. 18Malice veto

15 quality tests plus 3 security checks — the same 18 your audit export reports as tests_total.

05 — Where It Matters

Built for industries where wrong answers cost.

Click a card to see the pain, the solution, and what you actually get.

Compliance always depends on the overall system — AxiomSeal covers the memory layer (tamper-evident records, provenance, signed exports). No legal advice.

06 — Before / After

Same AI. Different outcome.

Without AxiomSeal

  • Hallucinated facts get stored
  • Contradictions surface in front of users
  • No audit trail when the model drifts
  • Compliance teams ask: prove it

With AxiomSeal

  • Memories pass 18 tests before storage
  • Contradictions caught and flagged at write-time
  • Every memory is signed (Sigma hash) + timestamped
  • Export-ready provenance for EU AI Act traceability

Plug AxiomSeal into your existing stack via MCP — your model stays the same, your reliability changes. Read the docs

07 — Architecture

Sits beside your stack. Not on top of it.

Your App / IDE
Where you build
MCP Protocol
One config line
AxiomSeal
Coherence layer
LLM
Claude / GPT / Gemini / Local
Memory Store
Signed + provenanced

Memory flows in both directions. AxiomSeal validates everything before it returns to your LLM and before it is stored.

08 — Connect

Connect to Claude in 30 seconds.

AxiomSeal is a remote MCP server. Add the URL, authorize with one click (OAuth — no API key to paste), and every memory Claude writes is truth-validated and cryptographically sealed.

MCP Server URL
https://mcp.axiomseal.com/mcp
Claude.ai & Desktop

Settings → Connectors → Add custom connector → paste the URL → Authorize.

Claude Code
Run
claude mcp add --transport http axiomseal https://mcp.axiomseal.com/mcp
Cursor

One-click install:

Add to Cursor

Also works with Windsurf, ChatGPT connectors, Gemini CLI and any other MCP client — see the setup guides.

09 — Pricing

Honest. Volume-based.

No surprise bills — hit your quota and writes pause, nothing gets charged. No lock-in. Memory export and full validation on every tier.

Free

CHF 0/forever
  • 500 stored memories
  • 1 project
  • 18 validation tests on every write
  • Community support
Start Free

Starter

CHF 29/month
  • 1,000 stored memories
  • 5 projects
  • Telegram integration
  • Email support
Choose Starter
Most Popular

Pro

CHF 99/month
  • 10,000 stored memories
  • 50 projects
  • Signed audit export (JSON/CSV/PDF)
  • Priority support
  • Advanced analytics
Choose Pro

Enterprise

Custom
  • Unlimited memories
  • Unlimited projects
  • SLA + DPA
  • Dedicated tenant
  • Dedicated success
Talk to sales
AxiomSeal Compliance — EU AI Act operations

Evidence your auditor can verify. Without you building it.

Everything in Pro, plus the EU AI Act ops suite: incident register with Art. 73 deadline tracking, risk flags, monitoring feed, inquiry reports (Art. 86) and an instructions annex generated from your live system. Signed exports (JSON/CSV/PDF), deletion certificates, 10-year audit-log retention, 50,000 stored memories — with DPA, priority compliance support and a personal onboarding session.

CHF 490 / month · cancel anytime

Personal AI Secretary — done-for-you

A working AI assistant, set up for you.

We set up the full coherence layer, a custom Telegram bot and a personal onboarding session for you — a hands-on service for solo practitioners (real estate, coaching, legal, healthcare) who'd rather not do the setup themselves.

CHF 349 / month · cancel anytime

Book a call

14-day free trial. No credit card. Switch or cancel anytime.

“I built AxiomSeal because I needed an AI assistant that wouldn't quietly drift. The world is choosing AI for decisions that hurt when AI is wrong. I refuse to ship one more system that cannot prove its own coherence.”

— Martin, founder. St. Gallen, Switzerland.

10 — Why this exists

Built by an operator, not a research lab.

AxiomSeal grew out of 9 months of running a persistent AI system in production. Every contradiction the system tried to commit became a test case. Every hallucination became a validation rule.

The result is not theoretical. It is a working coherence layer with 4,500+ validated memories in production. Every memory carries a SHA-512 seal — silent edits break the chain and get caught.

Every memory gets tested before it gets trusted. What fails validation is flagged or quarantined — not silently stored. That is the whole product.

11 — Questions

Questions you probably have.

No. It is a coherence layer that sits beside your AI assistant. It connects over the Model Context Protocol (MCP) — today via Claude Code, Cursor and Windsurf. GPT, Gemini and local-model setup guides are on the roadmap. AxiomSeal validates what goes in and what comes back.

12 — Get started

Stop shipping AI that contradicts itself.

Free tier, no credit card. Connect it to Claude Code or Cursor over MCP — full setup takes a few minutes.

Or talk to Martin directly — book a 20-min call.