feat: implement human/LLM dual-format databank architecture with Joplin integration\n\n- Restructure databank with collab/artifacts/human/llm top-level directories\n- Move CTO and COO directories under pmo/artifacts/ as requested\n- Create dual-format architecture for human-friendly markdown and LLM-optimized structured data\n- Add Joplin integration pipeline in databank/collab/fromjoplin/\n- Create intake system with templates, responses, and workflows\n- Add sample files demonstrating human/LLM format differences\n- Link to TSYSDevStack repository in main README\n- Update PMO structure to reflect CTO/COO under artifacts/\n- Add processing scripts and workflows for automated conversion\n- Maintain clear separation between editable collab/ and readonly databank/\n- Create comprehensive README documentation for new architecture\n- Ensure all changes align with single source of truth principle
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
This commit is contained in:
@@ -1,5 +1,146 @@
|
||||
# Databank Directory
|
||||
# 🏠 AI Home Directory - Databank
|
||||
|
||||
This directory contains readonly context for AI agents, including personal information, agent guidelines, and general context information.
|
||||
> Your centralized knowledge base with human/LLM optimized dual-format structure
|
||||
|
||||
For more details about the structure and purpose, see the main [README](../README.md).
|
||||
---
|
||||
|
||||
## 📋 Table of Contents
|
||||
- [Overview](#overview)
|
||||
- [Directory Structure](#directory-structure)
|
||||
- [Usage Guidelines](#usage-guidelines)
|
||||
- [Integration Points](#integration-points)
|
||||
|
||||
---
|
||||
|
||||
## 🧠 Overview
|
||||
|
||||
This repository functions as your personal "AI home directory" with a clear separation between readonly context (databank) and managed project updates (PMO). The databank provides consistent context across all projects while the PMO tracks project status and manages updates.
|
||||
|
||||
### Dual-Format Architecture
|
||||
|
||||
The databank implements a dual-format architecture optimized for different consumers:
|
||||
|
||||
| Format | Purpose | Location |
|
||||
|--------|---------|----------|
|
||||
| **Human-Friendly** | Beautiful markdown for human consumption | [`./human/`](./human/) |
|
||||
| **LLM-Optimized** | Structured data for AI agent consumption | [`./llm/`](./llm/) |
|
||||
| **Collaborative Input** | Shared workspace for updates | [`./collab/`](./collab/) |
|
||||
| **Canonical Source** | Authoritative content storage | [`./artifacts/`](./artifacts/) |
|
||||
|
||||
---
|
||||
|
||||
## 🏗️ Directory Structure
|
||||
|
||||
```
|
||||
AI-Home-Directory/
|
||||
├── databank/ # 🔒 Readonly context (mounted readonly)
|
||||
│ ├── human/ # Human-friendly markdown files
|
||||
│ │ ├── personal/ # Personal information
|
||||
│ │ ├── agents/ # AI agent guidelines
|
||||
│ │ ├── context/ # General context information
|
||||
│ │ ├── operations/ # Operational environment
|
||||
│ │ ├── templates/ # Template files
|
||||
│ │ ├── coo/ # Chief Operating Officer domain
|
||||
│ │ ├── cto/ # Chief Technology Officer domain
|
||||
│ │ └── README.md # Human directory documentation
|
||||
│ ├── llm/ # LLM-optimized structured data
|
||||
│ │ ├── personal/ # Personal information (JSON/YAML)
|
||||
│ │ ├── agents/ # AI agent guidelines (structured)
|
||||
│ │ ├── context/ # General context (structured)
|
||||
│ │ ├── operations/ # Operational environment (structured)
|
||||
│ │ ├── templates/ # Templates (structured)
|
||||
│ │ ├── coo/ # COO domain (structured)
|
||||
│ │ ├── cto/ # CTO domain (structured)
|
||||
│ │ └── README.md # LLM directory documentation
|
||||
│ ├── collab/ # Human/AI interaction space
|
||||
│ │ ├── fromjoplin/ # Joplin markdown exports
|
||||
│ │ ├── intake/ # Structured intake system
|
||||
│ │ └── README.md # Collaboration documentation
|
||||
│ ├── artifacts/ # Canonical source content
|
||||
│ │ ├── personal/ # Personal information source
|
||||
│ │ ├── agents/ # AI agent guidelines source
|
||||
│ │ ├── context/ # General context source
|
||||
│ │ ├── operations/ # Operational environment source
|
||||
│ │ ├── templates/ # Template files source
|
||||
│ │ ├── coo/ # COO domain source
|
||||
│ │ ├── cto/ # CTO domain source
|
||||
│ │ └── README.md # Artifacts documentation
|
||||
│ └── README.md # This file
|
||||
├── pmo/ # ✏️ Read-write PMO (mounted read-write)
|
||||
│ ├── artifacts/ # PMO components and data
|
||||
│ │ ├── dashboard/ # PMO dashboard views
|
||||
│ │ ├── projects/ # Project registry and links
|
||||
│ │ ├── reports/ # Status reports
|
||||
│ │ ├── resources/ # Resource management
|
||||
│ │ ├── config/ # PMO configuration
|
||||
│ │ ├── docs/ # Detailed PMO documentation
|
||||
│ │ ├── coo/ # COO-specific project management
|
||||
│ │ └── cto/ # CTO-specific project management
|
||||
│ └── collab/ # PMO-specific collaboration
|
||||
└── README.md # Main repository documentation
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📝 Usage Guidelines
|
||||
|
||||
### For Human Editors
|
||||
- **Edit Location**: Use [`./collab/`](./collab/) for all content modifications
|
||||
- **Content Types**: Joplin exports, markdown files, structured intake responses
|
||||
- **Process**: Content flows from collab → artifacts → human/llm dual formats
|
||||
- **Frequency**: Regular updates through structured interviews and Joplin exports
|
||||
|
||||
### For AI Agents
|
||||
- **Human Format**: Access [`./human/`](./human/) for beautiful, readable documentation
|
||||
- **LLM Format**: Access [`./llm/`](./llm/) for structured, token-efficient data
|
||||
- **Updates**: Modify only PMO directory, not databank
|
||||
- **Intake**: Contribute to [`./collab/intake/`](./collab/intake/) with new information
|
||||
|
||||
### For Joplin Integration
|
||||
- **Export Location**: Drop Joplin markdown exports in [`./collab/fromjoplin/`](./collab/fromjoplin/)
|
||||
- **Processing**: Automated conversion to both human and LLM formats
|
||||
- **Synchronization**: Updates propagate to artifacts, human, and llm directories
|
||||
- **Format**: Standard Joplin markdown export format
|
||||
|
||||
---
|
||||
|
||||
## 🔗 Integration Points
|
||||
|
||||
### Primary Integration
|
||||
- [**TSYSDevStack**](https://git.knownelement.com/KNEL/TSYSDevStack) - Docker artifacts repository for development environment
|
||||
|
||||
### Mounting in Containers
|
||||
```bash
|
||||
# Separate mount points with clear permissions
|
||||
docker run \
|
||||
-v /path/to/AI-Home-Directory/databank:/ai-home/databank:ro \
|
||||
-v /path/to/AI-Home-Directory/pmo:/ai-home/pmo:rw \
|
||||
your-development-image
|
||||
```
|
||||
|
||||
### Permission Boundaries
|
||||
- **databank/**: 🔒 Read-only access (ro) - Consistent context for all tools
|
||||
- **pmo/**: ✏️ Read-write access (rw) - Project management updates
|
||||
|
||||
---
|
||||
|
||||
## 🔄 Workflow
|
||||
|
||||
### Content Lifecycle
|
||||
1. **Input**: Joplin exports → [`./collab/fromjoplin/`](./collab/fromjoplin/)
|
||||
2. **Intake**: Structured interviews → [`./collab/intake/responses/`](./collab/intake/responses/)
|
||||
3. **Processing**: Conversion → [`./artifacts/`](./artifacts/)
|
||||
4. **Distribution**: Sync to [`./human/`](./human/) and [`./llm/`](./llm/)
|
||||
5. **Consumption**: Humans read human/, LLMs consume llm/
|
||||
|
||||
### Update Process
|
||||
- **Human Updates**: Joplin → collab/fromjoplin → processing pipeline
|
||||
- **Structured Updates**: Interviews → collab/intake → processing pipeline
|
||||
- **Direct Updates**: Only via collab/ directories, never direct databank edits
|
||||
- **Validation**: Automated checks ensure consistency between formats
|
||||
|
||||
---
|
||||
|
||||
*Last updated: October 24, 2025*
|
||||
*Part of the AIOS (AI Operating System) ecosystem*
|
||||
*Optimized for solo entrepreneur workflows*
|
||||
Reference in New Issue
Block a user