6ed69a3d48
Major changes: - Organized Python v1 implementation into v1/ subdirectory - Created Rust workspace with 9 modular crates: - wifi-densepose-core: Core types, traits, errors - wifi-densepose-signal: CSI processing, phase sanitization, FFT - wifi-densepose-nn: Neural network inference (ONNX/Candle/tch) - wifi-densepose-api: Axum-based REST/WebSocket API - wifi-densepose-db: SQLx database layer - wifi-densepose-config: Configuration management - wifi-densepose-hardware: Hardware abstraction - wifi-densepose-wasm: WebAssembly bindings - wifi-densepose-cli: Command-line interface Documentation: - ADR-001: Workspace structure - ADR-002: Signal processing library selection - ADR-003: Neural network inference strategy - DDD domain model with bounded contexts Testing: - 69 tests passing across all crates - Signal processing: 45 tests - Neural networks: 21 tests - Core: 3 doc tests Performance targets: - 10x faster CSI processing (~0.5ms vs ~5ms) - 5x lower memory usage (~100MB vs ~500MB) - WASM support for browser deployment
90 lines
1.7 KiB
Markdown
90 lines
1.7 KiB
Markdown
# Cross-Session Memory
|
|
|
|
## Purpose
|
|
Maintain context and learnings across Claude Code sessions for continuous improvement.
|
|
|
|
## Memory Features
|
|
|
|
### 1. Automatic State Persistence
|
|
At session end, automatically saves:
|
|
- Active agents and specializations
|
|
- Task history and patterns
|
|
- Performance metrics
|
|
- Neural network weights
|
|
- Knowledge base updates
|
|
|
|
### 2. Session Restoration
|
|
```javascript
|
|
// Using MCP tools for memory operations
|
|
mcp__claude-flow__memory_usage({
|
|
"action": "retrieve",
|
|
"key": "session-state",
|
|
"namespace": "sessions"
|
|
})
|
|
|
|
// Restore swarm state
|
|
mcp__claude-flow__context_restore({
|
|
"snapshotId": "sess-123"
|
|
})
|
|
```
|
|
|
|
**Fallback with npx:**
|
|
```bash
|
|
npx claude-flow hook session-restore --session-id "sess-123"
|
|
```
|
|
|
|
### 3. Memory Types
|
|
|
|
**Project Memory:**
|
|
- File relationships
|
|
- Common edit patterns
|
|
- Testing approaches
|
|
- Build configurations
|
|
|
|
**Agent Memory:**
|
|
- Specialization levels
|
|
- Task success rates
|
|
- Optimization strategies
|
|
- Error patterns
|
|
|
|
**Performance Memory:**
|
|
- Bottleneck history
|
|
- Optimization results
|
|
- Token usage patterns
|
|
- Efficiency trends
|
|
|
|
### 4. Privacy & Control
|
|
```javascript
|
|
// List memory contents
|
|
mcp__claude-flow__memory_usage({
|
|
"action": "list",
|
|
"namespace": "sessions"
|
|
})
|
|
|
|
// Delete specific memory
|
|
mcp__claude-flow__memory_usage({
|
|
"action": "delete",
|
|
"key": "session-123",
|
|
"namespace": "sessions"
|
|
})
|
|
|
|
// Backup memory
|
|
mcp__claude-flow__memory_backup({
|
|
"path": "./backups/memory-backup.json"
|
|
})
|
|
```
|
|
|
|
**Manual control:**
|
|
```bash
|
|
# View stored memory
|
|
ls .claude-flow/memory/
|
|
|
|
# Disable memory
|
|
export CLAUDE_FLOW_MEMORY_PERSIST=false
|
|
```
|
|
|
|
## Benefits
|
|
- 🧠 Contextual awareness
|
|
- 📈 Cumulative learning
|
|
- ⚡ Faster task completion
|
|
- 🎯 Personalized optimization |