~/.claude-dash/
├── projects/       # Project memory (indexes, summaries)
├── sessions/       # Session data, transcripts
├── learning/       # Corrections, preferences, calibration
├── mlx-tools/      # Local AI tools (Ollama-based)
├── skills/         # Skill definitions
├── logs/           # Service logs
├── indexes/        # HNSW search indexes
└── config.json     # Main configuration

memory_health action=status

# Check services
ps aux | grep -E "(watcher|gateway|ollama)"

# Check storage
du -sh ~/.claude-dash/*/

# Check recent errors
tail -20 ~/.claude-dash/logs/watcher-error.log

# Check gateway metrics
gateway_metrics format=summary

# Run session archival
python3 ~/.claude-dash/scripts/archive-sessions.py

# Run log rotation
~/.claude-dash/scripts/log-rotation.sh

# Trigger HNSW rebuild
hnsw_status action=rebuild project=gyst

# Run freshness check
workers_run worker=freshness project=gyst

# Run observation consolidation
workers_run worker=consolidate

# Restart watcher
~/.claude-dash/watcher/start-watcher.sh restart

# Restart gateway (via Claude settings or restart Claude)

{
  "projects": [...],
  "watcher": {
    "enabled": true,
    "ignorePatterns": [...],
    "scanIntervalMs": 5000
  }
}

{
  "id": "project-id",
  "displayName": "Project Name",
  "path": "/full/path/to/project",
  "memoryPath": "projects/project-id"
}

gateway_metrics format=detailed

learning_status component=all

rm -rf ~/.claude-dash/projects/{project}/*
# Watcher will rebuild on next file change

hnsw_status action=rebuild-all

# Backup first
cp -r ~/.claude-dash ~/.claude-dash.backup

# Then clear specific problematic data
rm ~/.claude-dash/sessions/observations.json
rm ~/.claude-dash/learning/corrections.json