Product
Learns · Knowledge Compiler Briefs · Context Engine Yours · Trust LayerSurfaces
Enterprise · Soma People · Self Family / team · Self+ M2M · Axis Protocol · NexusIP
Patent · P202631047 MVE · Minimum Viable Exposure .aix format ↗ Research Contact hello@thegeometrical.comS-04 · Axis · Agent memory
Autonomous agents and machine-to-machine workflows need to remember what they did, for whom, and what they were allowed to know. Axis gives them that memory — on the same runtime, under the same permissions.
What it does
01
What each agent did, for whom and why stays in the graph — so the next run starts where the last one left off.
02
Every read goes through Nexus: who is asking, for what scope and for which purpose. A revoked fact disappears from every path.
03
Every decision lands in an append-only, hash-chained audit, so you can prove what each agent saw — and what it didn’t.
Full documentation for Axis is in preparation. For early access, write to hello@thegeometrical.com.
If your agents need memory they can be held to, we would like to hear what you are building.