f2a02abf3e
Major reorganization to improve clarity and maintainability: ## Documentation - Created new simple README.md focused on Layer 1 - Added docs/ARCHITECTURE.md explaining multi-layer design - Moved LAYER1_REBUILD.md -> docs/LAYER1.md - Archived old documentation to docs/archive/: - CHANGELOG.md, QUICKSTART.md, STATUS.md, USAGE.md - DESIGN.md, README_CONFIG.md, ROADMAP.md, TECHNICAL_REVIEW.md - claude.md, test-mcp.sh ## Source Code - Moved unused .rs files to src/tmp/: - ai_interpreter.rs (Layer 2 - future) - companion.rs (Layer 4b - future) - game_formatter.rs (Layer 4a - future) - memory.rs (old implementation) - extended.rs (old MCP server) ## Result Clean root directory with only essential files: - README.md (simple, Layer 1 focused) - Cargo.toml - .gitignore - docs/ (organized documentation) - src/ (active code only) All Layer 1 functionality remains intact and tested.
1.8 KiB
1.8 KiB
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
# Build
cargo build --release
# Install (optional)
cp target/release/aigpt ~/.cargo/bin/
CLI Usage
# 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
# 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 for details.
Documentation
- Layer 1 Details - Technical details of current implementation
- Architecture - Multi-layer system design
Development
# Run tests
cargo test
# Build for release
cargo build --release
# Run with verbose logging
RUST_LOG=debug aigpt server
License
MIT
Author
syui