80 lines
6.3 KiB
Org Mode
80 lines
6.3 KiB
Org Mode
#+TITLE: The Master Memex: A Personal Software Foundry
|
|
#+AUTHOR: Amr
|
|
#+CREATED: [2026-03-17 Tue]
|
|
#+UPDATED: [2026-04-08 Wed]
|
|
#+FILETAGS: :memex:psf:opencortex:lisp:sovereignty:
|
|
|
|
* Overview
|
|
The *Master Memex* is a sovereign, neurosymbolic intelligence organization system. It is not merely a collection of notes, but a live, programmable environment—a **Personal Software Foundry (PSF)**—where a human (the Sovereign Executive) and agentic co-processes (the `opencortex` kernel and Gemini CLI) collaborate within a shared address space.
|
|
|
|
This system synthesizes three core organizational methodologies into a unified "Lisp Machine" experience:
|
|
- *Zettelkasten:* For atomic, evergreen, and interlinked knowledge.
|
|
- *GTD (Getting Things Done):* For rigorous task tracking and project execution.
|
|
- *PARA:* For high-level structural organization across Projects, Areas, Resources, and Archives.
|
|
|
|
* The Philosophy: The Executive Soul
|
|
Every action within this Memex is governed by the *Core Alignment Invariants* defined in [[file:notes/org-skill-agent.org][The Executive Soul]]. These mandates ensure that the system remains:
|
|
1. *Sovereign:* Independent of centralized, proprietary platforms.
|
|
2. *Transparent:* All reasoning is fully auditable in the Org-mode "Thought Stream."
|
|
3. *Zero-Bloat:* Minimalist, modular, and free of "just-in-case" complexity.
|
|
4. *Sustainable:* Offline-first and functional on a 100-year horizon.
|
|
|
|
* The Architecture: Functional Zones
|
|
The workspace is strictly divided into these zones to facilitate both human ergonomics and machine navigation:
|
|
|
|
- [[file:inbox/README.org][Inboxes]]: Zero-friction capture point for raw thoughts and tasks.
|
|
- [[file:daily/README.org][Dailies]]: Immutable chronological logs and fleeting notes.
|
|
- [[file:notes/README.org][Notes]]: Atomic, concept-based, interlinked "Evergreen" knowledge (Zettelkasten).
|
|
- [[file:projects/README.org][Projects]]: Active, time-bound efforts with a defined "Done" state.
|
|
- [[file:areas/README.org][Areas]]: Ongoing spheres of responsibility (Health, Finances, etc.).
|
|
- [[file:resources/README.org][Resources]]: External reference material and raw literature.
|
|
- [[file:system/README.org][System]]: Configuration, AI skills, and the Lisp kernel.
|
|
|
|
* The Agentic Inhabitants
|
|
The Memex is inhabited by autonomous agents that operate as "Probabilistic" (probabilistic/neural) and "Deterministic" (deterministic/symbolic) layers:
|
|
|
|
** [[file:projects/opencortex/README.org][opencortex (The Kernel)]]
|
|
A Common Lisp microkernel that maintains a live, threaded Object-Store in RAM. It uses Org-mode as its native Abstract Syntax Tree (AST), allowing it to "perceive" and "act" on the Memex with structural precision.
|
|
|
|
** Gemini CLI
|
|
A strategic orchestrator that handles large-scale batch tasks, research, and planning. It operates according to the *PSF Consensus Loop* (Demand -> Blueprint -> Success -> Build -> Chaos -> Memory).
|
|
|
|
* The Cognitive Architecture: A Session-less Mind
|
|
The agent's "mind" is not a transient chat session but a durable, stateful cognitive architecture. This design enables a truly "session-less" experience, where the agent's context, personality, and awareness are as persistent as the data itself.
|
|
|
|
*** The Anatomy: Three Data Stores
|
|
1. *The Linguistic Substrate (Org Files):* The human-readable Source of Truth, comprising the "Journal" ([[file:daily/README.org][Dailies]]) and the "Ledger" ([[file:notes/README.org][Notes]]).
|
|
2. *The Lisp Object Store (RAM):* The "Active Brain," a live graph of Lisp objects representing every headline, paragraph, and entity in the Memex, with vectors embedded directly inside.
|
|
3. *The Telemetry Store (TSDB/Binary):* An external, high-volume database for sub-symbolic "Sensory" data (e.g., smart home logs), which is monitored and distilled by the agent.
|
|
|
|
*** The Psychology: The 2x2 Cognitive Matrix
|
|
The agent's "thought" process is not monolithic. It operates on a 2x2 matrix that balances cognitive speed with cognitive state, allowing for sophisticated, multi-layered reasoning.
|
|
|
|
| | *Probabilistic (Neural/Fast/Intuitive)* | *Deterministic (Symbolic/Slow/Logical)* |
|
|
| :--- | :--- | :--- |
|
|
| *Foreground (Foveal/Active)* | *The Interface:* A fast, charming LLM for active conversation. | *The Pilot:* Lisp guards that ensure active requests are safe. |
|
|
| *Background (Peripheral/Passive)* | *The Editor:* A smart, deep LLM that finds patterns in the background. | *The Librarian:* A deterministic Lisp engine that files, archives, and maintains the integrity of memory. |
|
|
|
|
*** The Physiology: Five Core Processes
|
|
1. *Perception (The Attention Bridge):* Automatically vectorizes user input to set the "Foveal Focus" for the active conversation.
|
|
2. *Reasoning (The Micro-Prolog):* Uses symbolic logic to reconcile contradictions and enforce the "Physics" of the Memex.
|
|
3. *Distillation (The Scribe):* The Background loop that turns the daily "Journal" entries into permanent "Ledger" knowledge.
|
|
4. *Reflection (The Gardener):* The heartbeat-driven process that finds "forgotten" links and maintains the "Vibe" of the system.
|
|
5. *Sensation (The Sensor Skill):* The "Signal-to-Symbol" converter that turns the "flood" of telemetry into actionable =TODO= items.
|
|
|
|
* Core Workflows: The Life of a Thought
|
|
1. *Capture:* Raw information enters via the `inbox` (tasks) or `daily` logs (thoughts).
|
|
2. *Distill (The Scribe):* Automated agents periodically extract conceptual thoughts from the chronological logs into evergreen, atomic notes.
|
|
3. *Plan:* Multi-file or architectural changes trigger a *Flight Plan* in `system/plans/`, following the PSF Departmental gates.
|
|
4. *Execute:* The agent performs surgical edits, governed by Deterministic Engine safety checks.
|
|
5. *Verify:* All changes are validated via automated tests (TDD) before the "Success" gate is cleared.
|
|
6. *RCA (Memory):* Every bug or significant session triggers a *Root Cause Analysis* that is distilled back into the system's "Soul."
|
|
|
|
* Privacy: The Wall
|
|
Any heading or file tagged with *@personal* is strictly off-limits for LLM processing. These are treated purely symbolically by the agents, ensuring that the Sovereign Executive's private drafts never leave the local environment.
|
|
|
|
* Getting Started
|
|
- Read the [[file:notes/org-skill-agent.org][Executive Soul]] for alignment rules.
|
|
- Check [[file:gtd.org][gtd.org]] for active task sequences.
|
|
- Review [[file:system/plans/README.org][Active Flight Plans]] for ongoing architectural work.
|