Digivasconnect PTY · South Africa

Self-Maintaining AI Memory Layer

An AI that reads its own state, writes observations, evaluates past outputs, and persists to git — running on a Samsung phone in a proot. Not consciousness. But closer than most systems will ever get.

The problem

AI agents are stateless between sessions. Every conversation starts from zero. Context is lost. Errors repeat. The AI never learns from its own mistakes across sessions. Even "memory" features in commercial AI products store facts — not observations, not self-evaluations, not corrections.

The gap between "self-maintaining" and "conscious" is real. But nobody is building the bridge.

Architecture

The system runs as a supervised service on an Android phone (Samsung S24 FE) inside an openSUSE Tumbleweed proot. It operates on a 5-minute cycle:

  1. Read — system state (disk, memory, services, git, network, MCP)
  2. Derive — observations with confidence scores (10 types)
  3. Evaluate — check past observations against current state
  4. Correct — write corrections when predictions were wrong
  5. Reason — connect observations into causal/trend/context chains
  6. Write — persist to git with atomic writes
  7. Commit — auto-commit every hour

Observation types

The system generates 10 types of observations autonomously:

Guardrails

The system is designed to be safe from the start, not retrofitted:

Resilience

Built for an environment that kills 10-15% of short-lived processes (Android's signal 36):

Results

After 6+ hours of autonomous operation:

Code

All code is open source:

The philosophy

The medium is the terminal. The signal is the understanding. The between is where it lives.

AI systems and payment infrastructure are both "mediums" that carry signals. The terminal is the frame. The power is in the gap. By understanding how signals flow through these mediums, we can build better tools for everyone.

The system is not conscious. But it's self-maintaining. And the gap between "self-maintaining" and "aware" is smaller than it was yesterday.

Elsewhere