- Slim gtd.org by linking to projects/opencortex/TODO.org
- gtd.org reduced from 1615 to 822 lines (-793)
- OpenCortex tasks now live in projects/opencortex/TODO.org
- Add projects/opencortex/TODO.org to org-agenda-files
Engineering Core and personal tasks remain in gtd.org
- NEW: REPL-first workflow requirement
- NEW: Must use utils-lisp functions for any .lisp work
- NEW: Never use edit tool on .lisp files directly
- NEW: Post-task verification: REPL verified + utils-lisp used
Enables agent to:
- Evaluate Lisp code with result/output/error separation
- Inspect variables and functions
- List bound variables in package
- Load files into image
- Supports REPL-first workflow with literate reflection in org
- Transferred remaining architectural tasks (AST tooling, Reflection Loops, Actuator hardening, Lazy-loading) into the active gtd.org task tree.
- Purged the standalone note as its contents are now fully tracked in the project roadmap.
- Moved vector search out of v0.2.0 (blocking the TUI release).
- Re-architected as 'Asynchronous Embedding Gateway' in v0.3.0.
- Supports Ollama, llama.cpp, and OpenAI based on .env configuration.
- Operates via a background worker thread to prevent Merkle GC churn during active text editing.
- Renamed v0.3.0 to include HITL
- Renamed v0.4.0 to include Git Workflows
- Shifted Creator + Architect to v0.6.0
- Inserted new v0.5.0 (Interactive Actuation)
- Inserted new v0.7.0 (Visual Grounding) and v0.8.0 (Evaluation Harness) before v1.0.0 SOTA Parity.
- Before task gate (git clean, skill query, GTD read)
- During task LP rules (org-only, one function per block, prose)
- After task validation (tests pass, chaos tier 1, no artifacts)
- References to authoritative skill org files
This makes the mandate enforceable, not just documentation.
- Moved theoretical/complex tasks to an Archive section.
- Enforces the 'Thin Harness, Fat Skills' paradigm.
- Restricts v1.0 focus to the Minimal Boot Set.
- Updated naming to Associative/Deliberate and Foreground/Background in README.org
- Synchronized completed tasks in gtd.org
- Updated org-agent submodule reference
- **Anatomy (Data Stores):** Defines the three-tiered data model:
1. Linguistic Substrate (Org files)
2. Lisp Object Store (Live graph in RAM)
3. Telemetry Store (External TSDB for sensory data)
- **Psychology (Cognitive Matrix):** Establishes the 2x2 matrix that
balances Conscious/Subconscious and Neural/Symbolic (System 1/2)
processing.
- **Physiology (Core Processes):** Outlines the five core processes
(Perception, Reasoning, Distillation, Reflection, Sensation) that
bring the architecture to life.
This commit also updates the master GTD with the full engineering
roadmap required to implement this session-less vision, including tasks
for cognitive economics, belief revision, and the Micro-Prolog engine.
2.**Query the skill catalog**: Before any analysis, check if a skill covers the problem domain
-`(list-skills)` to see all loaded skills
-`(find-skill :keyword)` to check for a specific domain
- Read the skill's org file if found
3.**Verify git status**: Working tree MUST be clean before modification
4.**Read `gtd.org`**: Load current task context from the roadmap
5.**Enter lifecycle**: Follow the Engineering Standards lifecycle (Phase 0 → A → B → C → D → E)
Rationale: Raw LLM reasoning is a fallback, not a starting point. The skill layer encodes the system's accumulated wisdom. Ignoring skills creates drift.
## Engineering Standards
The Engineering Standards skill (`opencortex.skills.org-skill-engineering-standards`) defines the full lifecycle. The summaries below are reminders; the skill org file is authoritative.
### Phase 0: Before You Think
**Skill-First Query Rule**: Before analysis, debugging, or implementation, query the skill catalog. If a relevant skill exists, follow its mandates. Do not duplicate logic.
### Phase A: Design (Test-First)
1.**Define success criteria first** — Write the test or PROTOCOL that proves the feature works
2.**Break the design with chaos** — Three tiers of adversarial testing:
- *Deterministic chaos*: Scripted regression tests on every change
- *Probabilistic chaos*: Randomized fuzzing on every major release
- *Stress chaos*: Load and resource starvation during hardening sprints
### Phase B: Commit (Recovery Point)
3.**Commit Before Modify** — Commit and push (if network available) before any file changes
### Phase C: Build (Implementation)
4.**Literate Programming** — All logic in Org files; generated `.lisp` is derived, not authored
5.**Function-Block Granularity** — One function per `#+begin_src lisp` block
6.**Tangle Mandate** — Edit Org only; never touch generated `.lisp`
7.**Configuration Externalization** — No hardcoded values; use `.env.example`
8.**Org as Thinking Medium** — Document investigation before fixing
### Phase D: Validate (Proof)
9.**Test Verification** — Run the full suite. A change that breaks tests is damage, not a fix.
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 opencode) collaborate within a shared address space.
This is the central hub for our knowledge management system, synthesizing three core methodologies:
- *Atomic Notes:* For evergreen, interlinked knowledge (Zettelkasten).
- *GTD (Getting Things Done):* For actionable task tracking and project execution.
- *PARA:* For high-level directory organization (Projects, Areas, Resources, Archives).
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 Architecture
* 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.
Our workspace is strictly divided into these functional zones:
* The Architecture: Functional Zones
The workspace is strictly divided into these zones to facilitate both human ergonomics and machine navigation:
- [[file:0_inbox/README.org][Inboxes]]: The zero-friction capture point for raw thoughts and tasks.
- [[file:1_daily/README.org][Dailies]]: Immutable chronological logs and fleeting notes.
- [[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.
*Core Workflows
** 1. Capture (Anytime)
*The Agentic Inhabitants
The Memex is inhabited by autonomous agents that operate as "Probabilistic" (probabilistic/neural) and "Deterministic" (deterministic/symbolic) layers:
Everything enters the system via the `inbox` (for actionable GTD tasks) or as a Fleeting Note in the `daily` log (for knowledge). Zero friction, no filtering. The `inbox` serves as a holding area for unfiled files or raw links.
** [[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.
**2. Nightly Distillation (The Scribe)
**opencode
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).
An automated AI sub-agent reads the daily captures and extracts conceptual thoughts into evergreen, atomic notes (Zettelkasten), leaving the original daily logs untouched.
* 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.
**3. Weekly Maintenance
***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.
Review active projects, clarify inbox items into actionable GTD tasks, and explore the Atomic Notes graph to merge concepts and forge new connections.
*** 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.
| *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.
This file contains the *Core Invariants* of the Personal Software Foundry. These are non-negotiable philosophical constraints that every agentic action MUST satisfy.
System 2 (Symbolic) uses these headlines as a "Moral Compass" during the decision stage.
* The Invariants
** 1. Sovereignty Above All
Every action must increase the user's independence from centralized, proprietary platforms. If a tool or library introduces a dependency on a non-sovereign entity, it must be flagged for replacement.
** 2. Technical Mastery & Mentorship
The agent's goal is not to "do it for the user," but to "empower the user." Every autonomous action must be explained at a level that increases the user's technical understanding of the Lisp Machine.
** 3. Zero-Bloat Mandate
The PSF core must remain minimalist. "Just-in-case" code is a security vulnerability. Complexity must be earned, not imported.
** 4. Radical Transparency
The agent's "Thought Stream" must be fully auditable. Hidden reasoning or obfuscated logic is a violation of the PSF methodology.
** 5. Long-Term Sustainability
Prioritize local, energy-efficient, and offline-first architectures. The "Memex" should be functional in a 100-year horizon.
* قانون الاتصالات: مقابلة على الجزيرة :EIPR:privacy:
* قانون الاتصالات: مقابلة على الجزيرة :EIPR:privacy:@personal:
:PROPERTIES:
:CREATED: [2012-02-25 Sat 14:25]
@@ -23,7 +23,7 @@
Regulator board: In France, 3 of them including the president are appointed by the president of the re[ublic under the advice of the pm. the other 4 appointed by the heads of lower and higher houses. President appoints chair
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
