Update documentation: reflect Layers 1-3 completion
Updated README.md and ARCHITECTURE.md to reflect current implementation status. All three layers are now complete and functional. Changes: - README.md: Added Layer 2 (AI Memory) and Layer 3 (Big Five) features - README.md: Added MCP tools list and usage examples - README.md: Added Big Five personality traits explanation - ARCHITECTURE.md: Updated Layer 2 and 3 status to Complete - ARCHITECTURE.md: Updated implementation strategy phases - Archived old documentation in docs/archive/old-versions/ Current status: - Layer 1 ✅ Complete: Pure memory storage - Layer 2 ✅ Complete: AI interpretation + priority scoring - Layer 3 ✅ Complete: Big Five personality analysis - Layer 4 🔵 Planned: Game systems and companion features - Layer 5 🔵 Future: Distribution and sharing
This commit is contained in:
Claude
102
README.md
102
README.md
@@ -1,16 +1,31 @@
|
||||
# aigpt
|
||||
|
||||
Simple memory storage for Claude with MCP support.
|
||||
AI memory system with psychological analysis for Claude via MCP.
|
||||
|
||||
**Layer 1: Pure Memory Storage** - A clean, SQLite-based memory system with ULID identifiers.
|
||||
**Current: Layers 1-3 Complete** - Memory storage, AI interpretation, and personality analysis.
|
||||
|
||||
## Features
|
||||
|
||||
### Layer 1: Pure Memory Storage
|
||||
- 🗄️ **SQLite Storage**: Reliable database with ACID guarantees
|
||||
- 🔖 **ULID IDs**: Time-sortable, 26-character unique identifiers
|
||||
- 🔍 **Search**: Fast content-based search
|
||||
- 📝 **CRUD Operations**: Complete memory management
|
||||
|
||||
### Layer 2: AI Memory
|
||||
- 🧠 **AI Interpretation**: Claude interprets and evaluates memories
|
||||
- 📊 **Priority Scoring**: Importance ratings (0.0-1.0)
|
||||
- 🎯 **Smart Storage**: Memory + evaluation in one step
|
||||
|
||||
### Layer 3: Personality Analysis
|
||||
- 🔬 **Big Five Model**: Scientifically validated personality assessment
|
||||
- 📈 **Pattern Recognition**: Analyzes memory patterns to build user profile
|
||||
- 💾 **Historical Tracking**: Save and compare analyses over time
|
||||
|
||||
### General
|
||||
- 🛠️ **MCP Integration**: Works seamlessly with Claude Code
|
||||
- 🧪 **Well-tested**: Comprehensive test coverage
|
||||
- 🚀 **Simple & Fast**: Minimal dependencies, pure Rust
|
||||
|
||||
## Quick Start
|
||||
|
||||
@@ -47,30 +62,87 @@ aigpt stats
|
||||
claude mcp add aigpt /path/to/aigpt/target/release/aigpt server
|
||||
```
|
||||
|
||||
Then use in Claude Code:
|
||||
- "Remember that tomorrow will be sunny"
|
||||
- "Search for weather information"
|
||||
- "Show all my memories"
|
||||
## MCP Tools
|
||||
|
||||
### Layer 1: Basic Memory (6 tools)
|
||||
- `create_memory` - Simple memory creation
|
||||
- `get_memory` - Retrieve by ID
|
||||
- `list_memories` - List all memories
|
||||
- `search_memories` - Content-based search
|
||||
- `update_memory` - Update existing memory
|
||||
- `delete_memory` - Remove memory
|
||||
|
||||
### Layer 2: AI Memory (1 tool)
|
||||
- `create_ai_memory` - Create with AI interpretation and priority score
|
||||
|
||||
### Layer 3: Personality Analysis (2 tools)
|
||||
- `save_user_analysis` - Save Big Five personality analysis
|
||||
- `get_user_analysis` - Retrieve latest personality profile
|
||||
|
||||
## Usage Examples in Claude Code
|
||||
|
||||
### Layer 1: Simple Memory
|
||||
```
|
||||
Remember that the project deadline is next Friday.
|
||||
```
|
||||
Claude will use `create_memory` automatically.
|
||||
|
||||
### Layer 2: AI Memory with Evaluation
|
||||
```
|
||||
create_ai_memory({
|
||||
content: "Designed a new microservices architecture",
|
||||
ai_interpretation: "Shows technical creativity and strategic thinking",
|
||||
priority_score: 0.85
|
||||
})
|
||||
```
|
||||
|
||||
### Layer 3: Personality Analysis
|
||||
```
|
||||
# After accumulating memories, analyze personality
|
||||
save_user_analysis({
|
||||
openness: 0.8,
|
||||
conscientiousness: 0.7,
|
||||
extraversion: 0.4,
|
||||
agreeableness: 0.65,
|
||||
neuroticism: 0.3,
|
||||
summary: "High creativity and planning ability, introverted personality"
|
||||
})
|
||||
|
||||
# Retrieve analysis
|
||||
get_user_analysis()
|
||||
```
|
||||
|
||||
## Big Five Personality Traits
|
||||
|
||||
- **Openness**: Creativity, curiosity, openness to new experiences
|
||||
- **Conscientiousness**: Organization, planning, reliability
|
||||
- **Extraversion**: Social energy, assertiveness, outgoingness
|
||||
- **Agreeableness**: Cooperation, empathy, kindness
|
||||
- **Neuroticism**: Emotional stability (low = stable, high = sensitive)
|
||||
|
||||
Scores range from 0.0 to 1.0, where higher scores indicate stronger trait expression.
|
||||
|
||||
## Storage Location
|
||||
|
||||
Memories are stored in: `~/.config/syui/ai/gpt/memory.db`
|
||||
All data stored in: `~/.config/syui/ai/gpt/memory.db`
|
||||
|
||||
## Architecture
|
||||
|
||||
This is **Layer 1** of a planned multi-layer system:
|
||||
Multi-layer system design:
|
||||
|
||||
- **Layer 1** (Current): Pure memory storage
|
||||
- **Layer 2** (Planned): AI interpretation with priority scoring
|
||||
- **Layer 3** (Planned): User evaluation and diagnosis
|
||||
- **Layer 4** (Planned): Game systems and companion features
|
||||
- **Layer 1** ✅ Complete: Pure memory storage
|
||||
- **Layer 2** ✅ Complete: AI interpretation with priority scoring
|
||||
- **Layer 3** ✅ Complete: Big Five personality analysis
|
||||
- **Layer 4** 🔵 Planned: Game systems and companion features
|
||||
- **Layer 5** 🔵 Future: Distribution and sharing
|
||||
|
||||
See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for details.
|
||||
|
||||
## Documentation
|
||||
|
||||
- [Layer 1 Details](docs/LAYER1.md) - Technical details of current implementation
|
||||
- [Architecture](docs/ARCHITECTURE.md) - Multi-layer system design
|
||||
- [Layer 1 Details](docs/LAYER1.md) - Technical details of memory storage
|
||||
- [Old Versions](docs/archive/old-versions/) - Previous documentation
|
||||
|
||||
## Development
|
||||
|
||||
@@ -85,6 +157,10 @@ cargo build --release
|
||||
RUST_LOG=debug aigpt server
|
||||
```
|
||||
|
||||
## Design Philosophy
|
||||
|
||||
**"AI evolves, tools don't"** - This tool provides simple, reliable storage while AI (Claude) handles interpretation, evaluation, and analysis. The tool focuses on being maintainable and stable.
|
||||
|
||||
## License
|
||||
|
||||
MIT
|
||||
|
||||
@@ -12,29 +12,29 @@ aigptは、独立したレイヤーを積み重ねる設計です。各レイヤ
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────┐
|
||||
│ Layer 5: Distribution & Sharing │ Future
|
||||
│ Layer 5: Distribution & Sharing │ 🔵 Future
|
||||
│ (Game streaming, public/private) │
|
||||
├─────────────────────────────────────────┤
|
||||
│ Layer 4b: AI Companion │ Future
|
||||
│ Layer 4b: AI Companion │ 🔵 Planned
|
||||
│ (Romance system, personality growth) │
|
||||
├─────────────────────────────────────────┤
|
||||
│ Layer 4a: Game Systems │ Future
|
||||
│ Layer 4a: Game Systems │ 🔵 Planned
|
||||
│ (Ranking, rarity, XP, visualization) │
|
||||
├─────────────────────────────────────────┤
|
||||
│ Layer 3: User Evaluation │ Future
|
||||
│ (Personality diagnosis from patterns) │
|
||||
│ Layer 3: User Evaluation │ ✅ Complete
|
||||
│ (Big Five personality analysis) │
|
||||
├─────────────────────────────────────────┤
|
||||
│ Layer 2: AI Memory │ Future
|
||||
│ Layer 2: AI Memory │ ✅ Complete
|
||||
│ (Claude interpretation, priority_score)│
|
||||
├─────────────────────────────────────────┤
|
||||
│ Layer 1: Pure Memory Storage │ ✅ Current
|
||||
│ Layer 1: Pure Memory Storage │ ✅ Complete
|
||||
│ (SQLite, ULID, CRUD operations) │
|
||||
└─────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## Layer 1: Pure Memory Storage (Current)
|
||||
## Layer 1: Pure Memory Storage
|
||||
|
||||
**Status**: ✅ **Implemented & Tested**
|
||||
**Status**: ✅ **Complete**
|
||||
|
||||
### Purpose
|
||||
正確なデータの保存と参照。シンプルで信頼できる基盤。
|
||||
@@ -86,16 +86,16 @@ src/
|
||||
|
||||
---
|
||||
|
||||
## Layer 2: AI Memory (Planned)
|
||||
## Layer 2: AI Memory
|
||||
|
||||
**Status**: 🔵 **Planned**
|
||||
**Status**: ✅ **Complete**
|
||||
|
||||
### Purpose
|
||||
Claudeが記憶内容を解釈し、重要度を評価。
|
||||
Claudeが記憶内容を解釈し、重要度を評価。人間の記憶プロセス（記憶と同時に評価）を模倣。
|
||||
|
||||
### Extended Data Model
|
||||
```rust
|
||||
pub struct AIMemory {
|
||||
pub struct Memory {
|
||||
// Layer 1 fields
|
||||
pub id: String,
|
||||
pub content: String,
|
||||
@@ -103,63 +103,75 @@ pub struct AIMemory {
|
||||
pub updated_at: DateTime<Utc>,
|
||||
|
||||
// Layer 2 additions
|
||||
pub interpreted_content: String, // Claude's interpretation
|
||||
pub priority_score: f32, // 0.0 - 1.0
|
||||
pub psychological_factors: PsychologicalFactors,
|
||||
}
|
||||
|
||||
pub struct PsychologicalFactors {
|
||||
pub emotional_weight: f32, // 0.0 - 1.0
|
||||
pub personal_relevance: f32, // 0.0 - 1.0
|
||||
pub novelty: f32, // 0.0 - 1.0
|
||||
pub utility: f32, // 0.0 - 1.0
|
||||
pub ai_interpretation: Option<String>, // Claude's interpretation
|
||||
pub priority_score: Option<f32>, // 0.0 - 1.0
|
||||
}
|
||||
```
|
||||
|
||||
### MCP Tools (Additional)
|
||||
- `create_memory_with_ai` - Create with Claude interpretation
|
||||
- `reinterpret_memory` - Re-evaluate existing memory
|
||||
- `get_high_priority` - Get memories above threshold
|
||||
### MCP Tools
|
||||
- `create_ai_memory` - Create memory with AI interpretation and priority score
|
||||
- `content`: Memory content
|
||||
- `ai_interpretation`: Optional AI interpretation
|
||||
- `priority_score`: Optional priority (0.0-1.0)
|
||||
|
||||
### Implementation Strategy
|
||||
- Feature flag: `--features ai-memory`
|
||||
- Backward compatible with Layer 1
|
||||
### Philosophy
|
||||
"AIは進化しますが、ツールは進化しません" - AIが判断し、ツールは記録のみ。
|
||||
|
||||
### Implementation
|
||||
- Backward compatible with Layer 1 (Optional fields)
|
||||
- Automatic schema migration from Layer 1
|
||||
- Claude Code does interpretation (no external API)
|
||||
|
||||
---
|
||||
|
||||
## Layer 3: User Evaluation (Planned)
|
||||
## Layer 3: User Evaluation
|
||||
|
||||
**Status**: 🔵 **Planned**
|
||||
**Status**: ✅ **Complete**
|
||||
|
||||
### Purpose
|
||||
メモリパターンからユーザーの性格を診断。
|
||||
Layer 2のメモリパターンからユーザーの性格を分析。Big Five心理学モデルを使用。
|
||||
|
||||
### Diagnosis Types
|
||||
### Data Model
|
||||
```rust
|
||||
pub enum DiagnosisType {
|
||||
Innovator, // 革新者
|
||||
Philosopher, // 哲学者
|
||||
Pragmatist, // 実用主義者
|
||||
Explorer, // 探検家
|
||||
Protector, // 保護者
|
||||
Visionary, // 未来志向
|
||||
pub struct UserAnalysis {
|
||||
pub id: String,
|
||||
pub openness: f32, // 0.0-1.0: 創造性、好奇心
|
||||
pub conscientiousness: f32, // 0.0-1.0: 計画性、信頼性
|
||||
pub extraversion: f32, // 0.0-1.0: 外向性、社交性
|
||||
pub agreeableness: f32, // 0.0-1.0: 協調性、共感性
|
||||
pub neuroticism: f32, // 0.0-1.0: 神経質さ（低い=安定）
|
||||
pub summary: String, // 分析サマリー
|
||||
pub analyzed_at: DateTime<Utc>,
|
||||
}
|
||||
```
|
||||
|
||||
### Analysis
|
||||
- Memory content patterns
|
||||
- Priority score distribution
|
||||
- Creation frequency
|
||||
- Topic diversity
|
||||
### Big Five Model
|
||||
心理学で最も信頼性の高い性格モデル（OCEAN）：
|
||||
- **O**penness: 新しい経験への開かれさ
|
||||
- **C**onscientiousness: 誠実性、計画性
|
||||
- **E**xtraversion: 外向性
|
||||
- **A**greeableness: 協調性
|
||||
- **N**euroticism: 神経質さ
|
||||
|
||||
### MCP Tools (Additional)
|
||||
- `diagnose_user` - Run personality diagnosis
|
||||
- `get_user_profile` - Get analysis summary
|
||||
### Analysis Process
|
||||
1. Layer 2メモリを蓄積
|
||||
2. AIがパターンを分析（活動の種類、優先度の傾向など）
|
||||
3. Big Fiveスコアを推測
|
||||
4. 分析結果を保存
|
||||
|
||||
### MCP Tools
|
||||
- `save_user_analysis` - Save Big Five personality analysis
|
||||
- All 5 traits (0.0-1.0) + summary
|
||||
- `get_user_analysis` - Get latest personality profile
|
||||
|
||||
### Storage
|
||||
- SQLite table: `user_analyses`
|
||||
- Historical tracking: Compare analyses over time
|
||||
- Helper methods: `dominant_trait()`, `is_high()`
|
||||
|
||||
---
|
||||
|
||||
## Layer 4a: Game Systems (Planned)
|
||||
## Layer 4a: Game Systems
|
||||
|
||||
**Status**: 🔵 **Planned**
|
||||
|
||||
@@ -184,7 +196,7 @@ pub struct GameMemory {
|
||||
|
||||
---
|
||||
|
||||
## Layer 4b: AI Companion (Planned)
|
||||
## Layer 4b: AI Companion
|
||||
|
||||
**Status**: 🔵 **Planned**
|
||||
|
||||
@@ -236,21 +248,27 @@ pub struct Companion {
|
||||
- [x] Tests
|
||||
- [x] Documentation
|
||||
|
||||
### Phase 2: Layer 2 (Next)
|
||||
- [ ] Add AI interpretation fields to schema
|
||||
- [ ] Implement priority scoring logic
|
||||
- [ ] Create `create_memory_with_ai` tool
|
||||
- [ ] Update MCP server
|
||||
- [ ] Write tests for AI features
|
||||
### Phase 2: Layer 2 ✅ (Complete)
|
||||
- [x] Add AI interpretation fields to schema
|
||||
- [x] Implement priority scoring logic
|
||||
- [x] Create `create_ai_memory` tool
|
||||
- [x] Update MCP server
|
||||
- [x] Automatic schema migration
|
||||
- [x] Backward compatibility
|
||||
|
||||
### Phase 3: Layers 3-4 (Future)
|
||||
- [ ] User diagnosis system
|
||||
- [ ] Game mechanics
|
||||
- [ ] Companion system
|
||||
### Phase 3: Layer 3 ✅ (Complete)
|
||||
- [x] Big Five personality model
|
||||
- [x] UserAnalysis data structure
|
||||
- [x] user_analyses table
|
||||
- [x] `save_user_analysis` tool
|
||||
- [x] `get_user_analysis` tool
|
||||
- [x] Historical tracking support
|
||||
|
||||
### Phase 4: Layer 5 (Future)
|
||||
- [ ] Sharing mechanisms
|
||||
- [ ] Public/private modes
|
||||
### Phase 4: Layers 4-5 (Next)
|
||||
- [ ] Game mechanics (Layer 4a)
|
||||
- [ ] Companion system (Layer 4b)
|
||||
- [ ] Sharing mechanisms (Layer 5)
|
||||
- [ ] Public/private modes (Layer 5)
|
||||
|
||||
## Design Principles
|
||||
|
||||
@@ -330,5 +348,5 @@ src/
|
||||
---
|
||||
|
||||
**Version**: 0.2.0
|
||||
**Last Updated**: 2025-11-05
|
||||
**Current Layer**: 1
|
||||
**Last Updated**: 2025-11-06
|
||||
**Current Status**: Layers 1-3 Complete, Layer 4 Planned
|
||||
|
||||
334
docs/archive/old-versions/ARCHITECTURE.md.layer1
Normal file
334
docs/archive/old-versions/ARCHITECTURE.md.layer1
Normal file
@@ -0,0 +1,334 @@
|
||||
# Architecture: Multi-Layer Memory System
|
||||
|
||||
## Design Philosophy
|
||||
|
||||
aigptは、独立したレイヤーを積み重ねる設計です。各レイヤーは：
|
||||
|
||||
- **独立性**: 単独で動作可能
|
||||
- **接続性**: 他のレイヤーと連携可能
|
||||
- **段階的**: 1つずつ実装・テスト
|
||||
|
||||
## Layer Overview
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────┐
|
||||
│ Layer 5: Distribution & Sharing │ Future
|
||||
│ (Game streaming, public/private) │
|
||||
├─────────────────────────────────────────┤
|
||||
│ Layer 4b: AI Companion │ Future
|
||||
│ (Romance system, personality growth) │
|
||||
├─────────────────────────────────────────┤
|
||||
│ Layer 4a: Game Systems │ Future
|
||||
│ (Ranking, rarity, XP, visualization) │
|
||||
├─────────────────────────────────────────┤
|
||||
│ Layer 3: User Evaluation │ Future
|
||||
│ (Personality diagnosis from patterns) │
|
||||
├─────────────────────────────────────────┤
|
||||
│ Layer 2: AI Memory │ Future
|
||||
│ (Claude interpretation, priority_score)│
|
||||
├─────────────────────────────────────────┤
|
||||
│ Layer 1: Pure Memory Storage │ ✅ Current
|
||||
│ (SQLite, ULID, CRUD operations) │
|
||||
└─────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
## Layer 1: Pure Memory Storage (Current)
|
||||
|
||||
**Status**: ✅ **Implemented & Tested**
|
||||
|
||||
### Purpose
|
||||
正確なデータの保存と参照。シンプルで信頼できる基盤。
|
||||
|
||||
### Technology Stack
|
||||
- **Database**: SQLite with ACID guarantees
|
||||
- **IDs**: ULID (time-sortable, 26 chars)
|
||||
- **Language**: Rust with thiserror/anyhow
|
||||
- **Protocol**: MCP (Model Context Protocol) via stdio
|
||||
|
||||
### Data Model
|
||||
```rust
|
||||
pub struct Memory {
|
||||
pub id: String, // ULID
|
||||
pub content: String, // User content
|
||||
pub created_at: DateTime<Utc>,
|
||||
pub updated_at: DateTime<Utc>,
|
||||
}
|
||||
```
|
||||
|
||||
### Operations
|
||||
- `create()` - Insert new memory
|
||||
- `get(id)` - Retrieve by ID
|
||||
- `update()` - Update existing memory
|
||||
- `delete(id)` - Remove memory
|
||||
- `list()` - List all (sorted by created_at DESC)
|
||||
- `search(query)` - Content-based search
|
||||
- `count()` - Total count
|
||||
|
||||
### File Structure
|
||||
```
|
||||
src/
|
||||
├── core/
|
||||
│ ├── error.rs - Error types (thiserror)
|
||||
│ ├── memory.rs - Memory struct
|
||||
│ ├── store.rs - SQLite operations
|
||||
│ └── mod.rs - Module exports
|
||||
├── mcp/
|
||||
│ ├── base.rs - MCP server
|
||||
│ └── mod.rs - Module exports
|
||||
├── lib.rs - Library root
|
||||
└── main.rs - CLI application
|
||||
```
|
||||
|
||||
### Storage
|
||||
- Location: `~/.config/syui/ai/gpt/memory.db`
|
||||
- Schema: Single table with indexes on timestamps
|
||||
- No migrations (fresh start for Layer 1)
|
||||
|
||||
---
|
||||
|
||||
## Layer 2: AI Memory (Planned)
|
||||
|
||||
**Status**: 🔵 **Planned**
|
||||
|
||||
### Purpose
|
||||
Claudeが記憶内容を解釈し、重要度を評価。
|
||||
|
||||
### Extended Data Model
|
||||
```rust
|
||||
pub struct AIMemory {
|
||||
// Layer 1 fields
|
||||
pub id: String,
|
||||
pub content: String,
|
||||
pub created_at: DateTime<Utc>,
|
||||
pub updated_at: DateTime<Utc>,
|
||||
|
||||
// Layer 2 additions
|
||||
pub interpreted_content: String, // Claude's interpretation
|
||||
pub priority_score: f32, // 0.0 - 1.0
|
||||
pub psychological_factors: PsychologicalFactors,
|
||||
}
|
||||
|
||||
pub struct PsychologicalFactors {
|
||||
pub emotional_weight: f32, // 0.0 - 1.0
|
||||
pub personal_relevance: f32, // 0.0 - 1.0
|
||||
pub novelty: f32, // 0.0 - 1.0
|
||||
pub utility: f32, // 0.0 - 1.0
|
||||
}
|
||||
```
|
||||
|
||||
### MCP Tools (Additional)
|
||||
- `create_memory_with_ai` - Create with Claude interpretation
|
||||
- `reinterpret_memory` - Re-evaluate existing memory
|
||||
- `get_high_priority` - Get memories above threshold
|
||||
|
||||
### Implementation Strategy
|
||||
- Feature flag: `--features ai-memory`
|
||||
- Backward compatible with Layer 1
|
||||
- Claude Code does interpretation (no external API)
|
||||
|
||||
---
|
||||
|
||||
## Layer 3: User Evaluation (Planned)
|
||||
|
||||
**Status**: 🔵 **Planned**
|
||||
|
||||
### Purpose
|
||||
メモリパターンからユーザーの性格を診断。
|
||||
|
||||
### Diagnosis Types
|
||||
```rust
|
||||
pub enum DiagnosisType {
|
||||
Innovator, // 革新者
|
||||
Philosopher, // 哲学者
|
||||
Pragmatist, // 実用主義者
|
||||
Explorer, // 探検家
|
||||
Protector, // 保護者
|
||||
Visionary, // 未来志向
|
||||
}
|
||||
```
|
||||
|
||||
### Analysis
|
||||
- Memory content patterns
|
||||
- Priority score distribution
|
||||
- Creation frequency
|
||||
- Topic diversity
|
||||
|
||||
### MCP Tools (Additional)
|
||||
- `diagnose_user` - Run personality diagnosis
|
||||
- `get_user_profile` - Get analysis summary
|
||||
|
||||
---
|
||||
|
||||
## Layer 4a: Game Systems (Planned)
|
||||
|
||||
**Status**: 🔵 **Planned**
|
||||
|
||||
### Purpose
|
||||
ゲーム的要素で記憶管理を楽しく。
|
||||
|
||||
### Features
|
||||
- **Rarity Levels**: Common → Uncommon → Rare → Epic → Legendary
|
||||
- **XP System**: Memory creation earns XP
|
||||
- **Rankings**: Based on total priority score
|
||||
- **Visualization**: Game-style output formatting
|
||||
|
||||
### Data Additions
|
||||
```rust
|
||||
pub struct GameMemory {
|
||||
// Previous layers...
|
||||
pub rarity: RarityLevel,
|
||||
pub xp_value: u32,
|
||||
pub discovered_at: DateTime<Utc>,
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Layer 4b: AI Companion (Planned)
|
||||
|
||||
**Status**: 🔵 **Planned**
|
||||
|
||||
### Purpose
|
||||
育成可能な恋愛コンパニオン。
|
||||
|
||||
### Features
|
||||
- Personality types (Tsundere, Kuudere, Genki, etc.)
|
||||
- Relationship level (0-100)
|
||||
- Memory-based interactions
|
||||
- Growth through conversations
|
||||
|
||||
### Data Model
|
||||
```rust
|
||||
pub struct Companion {
|
||||
pub id: String,
|
||||
pub name: String,
|
||||
pub personality: CompanionPersonality,
|
||||
pub relationship_level: u8, // 0-100
|
||||
pub memories_shared: Vec<String>,
|
||||
pub last_interaction: DateTime<Utc>,
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Layer 5: Distribution (Future)
|
||||
|
||||
**Status**: 🔵 **Future Consideration**
|
||||
|
||||
### Purpose
|
||||
ゲーム配信や共有機能。
|
||||
|
||||
### Ideas
|
||||
- Share memory rankings
|
||||
- Export as shareable format
|
||||
- Public/private memory modes
|
||||
- Integration with streaming platforms
|
||||
|
||||
---
|
||||
|
||||
## Implementation Strategy
|
||||
|
||||
### Phase 1: Layer 1 ✅ (Complete)
|
||||
- [x] Core memory storage
|
||||
- [x] SQLite integration
|
||||
- [x] MCP server
|
||||
- [x] CLI interface
|
||||
- [x] Tests
|
||||
- [x] Documentation
|
||||
|
||||
### Phase 2: Layer 2 (Next)
|
||||
- [ ] Add AI interpretation fields to schema
|
||||
- [ ] Implement priority scoring logic
|
||||
- [ ] Create `create_memory_with_ai` tool
|
||||
- [ ] Update MCP server
|
||||
- [ ] Write tests for AI features
|
||||
|
||||
### Phase 3: Layers 3-4 (Future)
|
||||
- [ ] User diagnosis system
|
||||
- [ ] Game mechanics
|
||||
- [ ] Companion system
|
||||
|
||||
### Phase 4: Layer 5 (Future)
|
||||
- [ ] Sharing mechanisms
|
||||
- [ ] Public/private modes
|
||||
|
||||
## Design Principles
|
||||
|
||||
1. **Simplicity First**: Each layer adds complexity incrementally
|
||||
2. **Backward Compatibility**: New layers don't break old ones
|
||||
3. **Feature Flags**: Optional features via Cargo features
|
||||
4. **Independent Testing**: Each layer has its own test suite
|
||||
5. **Clear Boundaries**: Layers communicate through defined interfaces
|
||||
|
||||
## Technology Choices
|
||||
|
||||
### Why SQLite?
|
||||
- ACID guarantees
|
||||
- Better querying than JSON
|
||||
- Built-in indexes
|
||||
- Single-file deployment
|
||||
- No server needed
|
||||
|
||||
### Why ULID?
|
||||
- Time-sortable (unlike UUID v4)
|
||||
- Lexicographically sortable
|
||||
- 26 characters (compact)
|
||||
- No collision concerns
|
||||
|
||||
### Why Rust?
|
||||
- Memory safety
|
||||
- Performance
|
||||
- Excellent error handling
|
||||
- Strong type system
|
||||
- Great tooling (cargo, clippy)
|
||||
|
||||
### Why MCP?
|
||||
- Standard protocol for AI tools
|
||||
- Works with Claude Code/Desktop
|
||||
- Simple stdio-based communication
|
||||
- No complex networking
|
||||
|
||||
## Future Considerations
|
||||
|
||||
### Potential Enhancements
|
||||
- Full-text search (SQLite FTS5)
|
||||
- Tag system
|
||||
- Memory relationships/links
|
||||
- Export/import functionality
|
||||
- Multiple databases
|
||||
- Encryption for sensitive data
|
||||
|
||||
### Scalability
|
||||
- Layer 1: Handles 10K+ memories easily
|
||||
- Consider pagination for Layer 4 (UI display)
|
||||
- Indexing strategy for search performance
|
||||
|
||||
## Development Guidelines
|
||||
|
||||
### Adding a New Layer
|
||||
|
||||
1. **Design**: Document data model and operations
|
||||
2. **Feature Flag**: Add to Cargo.toml
|
||||
3. **Schema**: Extend database schema (migrations)
|
||||
4. **Implementation**: Write code in new module
|
||||
5. **Tests**: Comprehensive test coverage
|
||||
6. **MCP Tools**: Add new MCP tools if needed
|
||||
7. **Documentation**: Update this file
|
||||
|
||||
### Code Organization
|
||||
|
||||
```
|
||||
src/
|
||||
├── core/ # Layer 1: Pure storage
|
||||
├── ai/ # Layer 2: AI features (future)
|
||||
├── evaluation/ # Layer 3: User diagnosis (future)
|
||||
├── game/ # Layer 4a: Game systems (future)
|
||||
├── companion/ # Layer 4b: Companion (future)
|
||||
└── mcp/ # MCP server (all layers)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**Version**: 0.2.0
|
||||
**Last Updated**: 2025-11-05
|
||||
**Current Layer**: 1
|
||||
94
docs/archive/old-versions/README.md.layer1
Normal file
94
docs/archive/old-versions/README.md.layer1
Normal file
@@ -0,0 +1,94 @@
|
||||
# aigpt
|
||||
|
||||
Simple memory storage for Claude with MCP support.
|
||||
|
||||
**Layer 1: Pure Memory Storage** - A clean, SQLite-based memory system with ULID identifiers.
|
||||
|
||||
## Features
|
||||
|
||||
- 🗄️ **SQLite Storage**: Reliable database with ACID guarantees
|
||||
- 🔖 **ULID IDs**: Time-sortable, 26-character unique identifiers
|
||||
- 🔍 **Search**: Fast content-based search
|
||||
- 🛠️ **MCP Integration**: Works seamlessly with Claude Code
|
||||
- 🧪 **Well-tested**: Comprehensive test coverage
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Installation
|
||||
|
||||
```bash
|
||||
# Build
|
||||
cargo build --release
|
||||
|
||||
# Install (optional)
|
||||
cp target/release/aigpt ~/.cargo/bin/
|
||||
```
|
||||
|
||||
### CLI Usage
|
||||
|
||||
```bash
|
||||
# Create a memory
|
||||
aigpt create "Remember this information"
|
||||
|
||||
# List all memories
|
||||
aigpt list
|
||||
|
||||
# Search memories
|
||||
aigpt search "keyword"
|
||||
|
||||
# Show statistics
|
||||
aigpt stats
|
||||
```
|
||||
|
||||
### MCP Integration with Claude Code
|
||||
|
||||
```bash
|
||||
# Add to Claude Code
|
||||
claude mcp add aigpt /path/to/aigpt/target/release/aigpt server
|
||||
```
|
||||
|
||||
Then use in Claude Code:
|
||||
- "Remember that tomorrow will be sunny"
|
||||
- "Search for weather information"
|
||||
- "Show all my memories"
|
||||
|
||||
## Storage Location
|
||||
|
||||
Memories are stored in: `~/.config/syui/ai/gpt/memory.db`
|
||||
|
||||
## Architecture
|
||||
|
||||
This is **Layer 1** of a planned multi-layer system:
|
||||
|
||||
- **Layer 1** (Current): Pure memory storage
|
||||
- **Layer 2** (Planned): AI interpretation with priority scoring
|
||||
- **Layer 3** (Planned): User evaluation and diagnosis
|
||||
- **Layer 4** (Planned): Game systems and companion features
|
||||
|
||||
See [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) for details.
|
||||
|
||||
## Documentation
|
||||
|
||||
- [Layer 1 Details](docs/LAYER1.md) - Technical details of current implementation
|
||||
- [Architecture](docs/ARCHITECTURE.md) - Multi-layer system design
|
||||
|
||||
## Development
|
||||
|
||||
```bash
|
||||
# Run tests
|
||||
cargo test
|
||||
|
||||
# Build for release
|
||||
cargo build --release
|
||||
|
||||
# Run with verbose logging
|
||||
RUST_LOG=debug aigpt server
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
MIT
|
||||
|
||||
## Author
|
||||
|
||||
syui
|
||||
Reference in New Issue
Block a user