with one click
databases
View all Claudia memory databases, switch between them, manage isolation. Triggers on "which database?", "switch workspace", "show databases", "list databases".
Menu
View all Claudia memory databases, switch between them, manage isolation. Triggers on "which database?", "switch workspace", "show databases", "list databases".
Launch the Brain Monitor TUI, a real-time terminal dashboard for watching Claudia's memory system. Triggers on "brain monitor", "show dashboard", "memory dashboard", "terminal brain". See also: `brain` for a 3D graph view in the browser.
Launch the Brain Visualizer, a real-time 3D view of memory and relationships. Triggers on "show your brain", "visualize memory", "open the brain", "memory graph". See also: `brain-monitor` for a terminal dashboard alternative.
Process meeting notes or transcript to extract decisions, commitments, and insights. Use when user shares transcript or says "capture this meeting", "here are my notes from the call". See also: `meeting-prep` for pre-call briefings; `follow-up-draft` for post-meeting emails.
Check memory system health and troubleshoot connectivity issues. Use when memory commands aren't working, at session start if something seems wrong, or when user asks about memory status. See also: `memory-health` for the data-quality dashboard once connectivity is confirmed.
Draft an email response with tone matching the relationship context. Shows draft for approval before sending. Use when user says "draft a reply", "respond to this email", "write a response to [person]", or shares an email and asks for help replying. See also: `follow-up-draft` for post-meeting thank-yous with meeting context.
Store a document, email, or text for future reference with entity linking and provenance. See also: `ingest-sources` for multiple files; `capture-meeting` if it's meeting notes; `summarize-doc` to get a summary without filing.
| name | databases |
| description | View all Claudia memory databases, switch between them, manage isolation. Triggers on "which database?", "switch workspace", "show databases", "list databases". |
| argument-hint | [list|use|info|delete] [hash] |
| effort-level | low |
View all Claudia memory databases, see what's in each, and switch between them.
Triggers: /databases, /db, "show databases", "list my databases", "switch database", "which database am I using?"
Parse the user's input to determine the subcommand:
| Input | Subcommand |
|---|---|
/databases, /db, "show databases", "list databases" | list |
/databases use <hash>, "switch to ", "use database " | use |
/databases info <hash>, "database info", "show database " | info |
/databases delete <hash>, "delete database " | delete |
If no subcommand is clear, default to list.
Scan all Claudia databases and display their stats.
# List production databases
ls -la ~/.claudia/memory/*.db 2>/dev/null || echo "NO_PROD_DBS"
# List demo databases
ls -la ~/.claudia/demo/*.db 2>/dev/null || echo "NO_DEMO_DBS"
The currently active database is determined by the workspace directory. The CLI hashes the project path to find the right database:
# Check current working directory to compute expected hash
pwd | shasum -a 256 | head -c 12
For each .db file found, query it directly using sqlite3:
# For each database file, extract stats
# Replace <db_path> with actual path
sqlite3 "<db_path>" "
SELECT
(SELECT value FROM _meta WHERE key = 'workspace_path') as workspace,
(SELECT COUNT(*) FROM entities WHERE type = 'person') as people,
(SELECT COUNT(*) FROM memories) as memories,
(SELECT COUNT(*) FROM entities) as entities,
(SELECT MAX(created_at) FROM memories) as last_memory
"
If _meta table doesn't exist or workspace_path is NULL, show "Unknown (legacy)".
# Get file sizes in human-readable format
du -h ~/.claudia/memory/*.db 2>/dev/null
du -h ~/.claudia/demo/*.db 2>/dev/null
Present the results in a clean table:
## Claudia Databases
### Production (~/.claudia/memory/)
| # | Hash | Workspace | Size | People | Memories | Last Active |
|---|------|-----------|------|--------|----------|-------------|
| > | a1b2c3d4e5f6 | ~/projects/startup | 2.3 MB | 18 | 127 | 2h ago |
| | 9z8y7x6w5v4u | ~/work/client-a | 890 KB | 3 | 22 | 3d ago |
| | x7y8z9a0b1c2 | Unknown (legacy) | 156 KB | 0 | 5 | 14d ago |
### Demo (~/.claudia/demo/)
| # | File | Description | Size | People | Memories | Last Active |
|---|------|-------------|------|--------|----------|-------------|
| | claudia-demo.db | Global demo | 1.1 MB | 12 | 19 | 1d ago |
> = currently active
---
**Actions:**
- `/databases use <hash>` - Switch to a different database
- `/databases info <hash>` - Deep dive into a specific database
- `/databases delete <hash>` - Delete a database (with confirmation)
Format "Last Active" as relative time (e.g., "2h ago", "3d ago", "14d ago").
Switch to a different database by setting the CLAUDIA_DB_OVERRIDE environment variable.
ls ~/.claudia/memory/<hash>.db 2>/dev/null || ls ~/.claudia/demo/<hash>.db 2>/dev/null
If not found, report error:
Database '<hash>' not found. Run `/databases` to see available databases.
sqlite3 "~/.claudia/memory/<hash>.db" "SELECT value FROM _meta WHERE key = 'workspace_path'" 2>/dev/null || echo "Unknown workspace"
Before switching, warn the user:
**Database Switch**
You're about to switch from:
**Current:** [current workspace path] ([current hash])
To:
**Target:** [target workspace path] ([target hash])
This will set `CLAUDIA_DB_OVERRIDE` in your environment.
**You'll need to restart Claude Code for the change to take effect.**
Proceed? (yes/no)
If confirmed, update the .claude/settings.local.json file to add CLAUDIA_DB_OVERRIDE environment variable:
Read the current settings, then add or update the environment variable:
# Check if settings exist
cat .claude/settings.local.json 2>/dev/null || echo "NO_SETTINGS"
Then edit the file to add:
{
"env": {
"CLAUDIA_DB_OVERRIDE": "/Users/kamil/.claudia/memory/<hash>.db"
}
}
**Database switched to:** [target hash]
**Workspace:** [target workspace path]
**Action required:** Restart Claude Code for the change to take effect.
- Exit this session (type `/exit` or close terminal)
- Start a new `claude` session
To switch back to your original database, run `/databases use <original-hash>`.
Show detailed statistics about a specific database.
ls ~/.claudia/memory/<hash>.db 2>/dev/null || ls ~/.claudia/demo/<hash>.db 2>/dev/null
sqlite3 "<db_path>" "
-- Workspace info
SELECT 'workspace' as section, key, value FROM _meta;
-- Entity breakdown
SELECT 'entity_type' as section, type, COUNT(*) as count FROM entities GROUP BY type;
-- Memory breakdown
SELECT 'memory_type' as section, type, COUNT(*) as count FROM memories GROUP BY type;
-- Relationship count
SELECT 'relationships' as section, 'total' as type, COUNT(*) as count FROM relationships;
-- Episode count
SELECT 'episodes' as section, 'total' as type, COUNT(*) as count FROM episodes;
-- Pattern count
SELECT 'patterns' as section, 'total' as type, COUNT(*) as count FROM patterns;
-- Prediction count (active)
SELECT 'predictions' as section, 'active' as type, COUNT(*) as count FROM predictions WHERE expires_at > datetime('now') OR expires_at IS NULL;
-- Recent activity
SELECT 'recent_24h' as section, 'memories' as type, COUNT(*) as count FROM memories WHERE created_at > datetime('now', '-24 hours');
"
sqlite3 "<db_path>" "
SELECT name, type, importance,
(SELECT COUNT(*) FROM memory_entities WHERE entity_id = entities.id) as memory_count
FROM entities
ORDER BY importance DESC, memory_count DESC
LIMIT 15
"
## Database Info: [hash]
**Workspace:** [path]
**Size:** [file size]
**Created:** [created_at from _meta]
**Last Activity:** [last memory created_at]
### Entity Breakdown
| Type | Count |
|------|-------|
| person | 18 |
| organization | 5 |
| project | 12 |
| concept | 3 |
### Memory Breakdown
| Type | Count |
|------|-------|
| fact | 89 |
| preference | 12 |
| observation | 8 |
| learning | 5 |
| commitment | 13 |
### Other Stats
- **Relationships:** 45
- **Episodes:** 23
- **Patterns:** 8
- **Active Predictions:** 3
- **Activity (24h):** 7 new memories
### Top Entities
| Name | Type | Memories |
|------|------|----------|
| Sarah Chen | person | 34 |
| Acme Corp | organization | 22 |
| Project Alpha | project | 18 |
...
---
**Actions:**
- `/databases use [hash]` - Switch to this database
- `/databases delete [hash]` - Delete this database
Delete a database with explicit confirmation.
If the user is trying to delete the currently active database, refuse:
Cannot delete the currently active database.
Switch to a different database first using `/databases use <other-hash>`, then try again.
ls ~/.claudia/memory/<hash>.db 2>/dev/null || ls ~/.claudia/demo/<hash>.db 2>/dev/null
Query stats to show what will be lost:
sqlite3 "<db_path>" "
SELECT
(SELECT value FROM _meta WHERE key = 'workspace_path') as workspace,
(SELECT COUNT(*) FROM entities WHERE type = 'person') as people,
(SELECT COUNT(*) FROM memories) as memories,
(SELECT COUNT(*) FROM episodes) as episodes
"
**Delete Database**
You're about to **permanently delete** the database:
**Hash:** [hash]
**Workspace:** [workspace path]
**Contains:**
- [X] people
- [Y] memories
- [Z] conversation episodes
**This action cannot be undone.**
Type "DELETE [hash]" to confirm, or "cancel" to abort.
Wait for the user to type the exact confirmation string.
Only after explicit confirmation:
rm ~/.claudia/memory/<hash>.db
rm ~/.claudia/memory/<hash>.db-shm 2>/dev/null
rm ~/.claudia/memory/<hash>.db-wal 2>/dev/null
**Database deleted:** [hash]
The following files were removed:
- ~/.claudia/memory/[hash].db
- ~/.claudia/memory/[hash].db-shm (if existed)
- ~/.claudia/memory/[hash].db-wal (if existed)
~ for readabilityNo databases found:
No Claudia databases found.
This could mean:
- Claudia hasn't been set up yet (run `npx get-claudia`)
- The Claudia CLI hasn't been used yet
- Databases are in a non-standard location
Expected locations:
- Production: ~/.claudia/memory/*.db
- Demo: ~/.claudia/demo/*.db
Database query fails:
Could not query database [hash]: [error message]
The database file may be corrupted or locked by another process.
Permission denied:
Permission denied when accessing [path].
Check file permissions: `ls -la ~/.claudia/memory/`