build-team
Propose and, after approval, configure a personalized team of Codex subagent roles based on the user's profile, goals, and working style.
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.
$ npx -y skills add kbanc85/claudia --skill brain --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/brainContext preview
The summary Claude sees to decide when to auto-load this skill.
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.
name: brain description: "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." effort-level: medium
Launch the Claudia Brain Visualizer, a real-time 3D cosmos visualization of my memory system showing entities, relationships, memories, and patterns as a swirling interactive force-directed graph.
**Triggers:** `/brain`, "show me your brain", "visualize memory", "open the brain", "memory graph"
---
The visualizer is a single Express server (`server.js`) in `~/.claudia/visualizer/` that serves both the API (reads SQLite directly) and the pre-built 3D frontend from `dist/`. One process, one port (3849).
---
if curl -s http://localhost:3849/health > /dev/null 2>&1; then echo "ALREADY_RUNNING" else echo "NOT_RUNNING" fi
VISUALIZER_DIR=""
for dir in \
"$HOME/.claudia/visualizer" \
"$(npm root -g 2>/dev/null)/get-claudia/visualizer"; do
if [ -d "$dir" ] && [ -f "$dir/server.js" ]; then
VISUALIZER_DIR="$dir"
break
fi
done
if [ -z "$VISUALIZER_DIR" ]; then
echo "VISUALIZER_NOT_FOUND"
else
echo "VISUALIZER_FOUND:$VISUALIZER_DIR"
fiPROJECT_DIR="$(pwd)" cd "$VISUALIZER_DIR" # Install deps if needed if [ ! -d "node_modules" ]; then echo "Installing dependencies..." npm install --production 2>&1 fi # Start server with --open to auto-launch browser nohup node server.js --project-dir "$PROJECT_DIR" --open > /tmp/claudia-brain.log 2>&1 & sleep 2 # Verify it started if curl -s http://localhost:3849/health > /dev/null 2>&1; then echo "STARTED" else echo "FAILED" tail -10 /tmp/claudia-brain.log fi
If the server was already running, just open the browser:
open "http://localhost:3849" 2>/dev/null || xdg-open "http://localhost:3849" 2>/dev/null || echo "OPEN_MANUALLY:http://localhost:3849"
---
**If already running:**
Your brain is live at http://localhost:3849
**If started successfully:**
**Brain Visualizer** Live at http://localhost:3849 Viewing database for: [PROJECT_DIR] What you're seeing: - **Entities** (people, orgs, projects, concepts) as colored nodes, size scales with importance - **Relationships** as arcing edges with traveling pulse particles - **Patterns** as wireframe clusters - **Starfield** background, the galaxy is just ambiance **Controls:** - Click any node to see details, memories, and relationships - Search bar (top left) to find specific entities, camera flies to matches - H = toggle HUD, R = reset camera, F = fullscreen, Esc = close panel - The graph updates live as I learn new things
**If visualizer not found:**
The Brain Visualizer isn't installed at ~/.claudia/visualizer/. To install: run `npx get-claudia` again, or manually copy the visualizer directory: 1. Copy `visualizer/` from the get-claudia package to `~/.claudia/visualizer/` 2. Run `npm install --production` there 3. Try `/brain` again
**If server failed to start:**
The server couldn't start. Check the log: ```bash tail -50 /tmp/claudia-brain.log
Common issues:
--- ## Tone Treat this like showing someone something cool. A little proud of it. "Want to see what your memory graph looks like?" energy.
Terminal-based AI chief of staff. Remembers relationships, tracks commitments, helps you think strategically. Runs on Claude Code.
Repo: kbanc85/claudia
Propose and, after approval, configure a personalized team of Codex subagent roles based on the user's profile, goals, and working style.
Use Claudia's identity, persistent local memory, relationship context, project routing, judgment rules, and strategic operating style. Trigger for personal,…
Inspect Claudia's unified production memory database and backups. Use for database identity, health, counts, schema, WAL, backup inventory, or an explicitly…
Run Claudia's required first-conversation setup. Use automatically before substantive work whenever the current Claudia workspace has no context/me.md,…
Iteratively improve a local artifact (draft, document, page) by running a hill-climbing loop. The user names the artifact, the evaluator, and the budget.…
Launch the Brain Monitor TUI, a real-time terminal dashboard for watching Claudia's memory system. Triggers on \"brain monitor\", \"show dashboard\", \"memory…