vibrating·memory

Memory architecture for AI agents

An agent's memory that lives entirely in text files.

No database. No vectors. No proprietary model. Vibrating Memory is an architecture of memory cards — facts, index, portrait, instant perceptions — designed to run on any popular LLM capable of following rules written in natural language.

origin 2026-08-26 format md · log · jsonl author Olivier Deschamps, Cybenergie

Three deliberate constraints

What makes the system reproducible by anyone

01 — storage

No database engine

Markdown for cards, JSONL for logs, raw logs for technical monitoring. Nothing to install, nothing to maintain, nothing to run.

02 — model

Popular LLMs

No exotic capability required. If a model can read rules and follow them consistently, it can carry the system.

03 — logic

Natural language, no code

The cards are text an LLM understands directly. Code stays at the edges — reading a file, handling an API call — never inside the memory logic itself.

A documented origin

Traced priority, not just claimed

  • March 2026

    Early experimentation. Prefix-based context caching on live conversational video avatars (LiveKit, Groq) — the base intuition: separate what almost never changes from what changes every turn.

  • August 26, 2026

    Formalization of the unified concept. The architecture is named Vibrating Memory. First A/B/I/S/C/E cards written and versioned, designed specifically around the Claude API's explicit cache mechanism.

  • August 27–28, 2026

    System expansion. Additional factual cards (portrait, self-awareness, other agents, tasks, skills) and early work on sensory and temporal memory.

  • Ongoing

    Public documentation. Progressive publication of the Vibrating Memory series — architecture, factual cards, sensory memory.

Journal

The series, as it's published