create-walle
v0.9.27
Published
CTM + Wall-E — AI coding dashboard and personal digital twin agent. Multi-agent terminal for Claude Code, Codex, Gemini, Aider, OpenCode, and more, plus prompt editor, task queue, remote phone and tablet access, code/doc review, and an agent that learns f
Maintainers
Readme
create-walle
Set up CTM + Wall-E in one command — a browser-based command center for AI coding agents, remote phone and tablet access, review workflows, and a personal AI agent that builds a searchable second brain from your work life.
What You Get
CTM (Coding Task Manager)
A web dashboard for running and managing AI coding sessions across multiple providers.
- Terminal Multiplexer — Run Claude Code, Codex, Gemini CLI, Aider, OpenCode, Cursor Agent, and more side by side with live status, persistent scrollback, model switching, and AI-generated titles
- Prompt Editor — Save, version, and organize prompts with folders, tags, chains, templates, and AI search
- Task Queue — Queue prompts for sequential execution with auto-advance when the agent finishes, or step through manually
- Approval Workflows — Auto-approve tool-use requests based on learned rules; uncertain cases escalate to you
- Remote Phone & Tablet Access — Pair your phone or tablet with a QR code and use a responsive CTM UI over Microsoft Dev Tunnels, Tailscale, Cloudflare Tunnel, or Walle Remote, with live prompts and model controls
- Code & Doc Review — Review git diffs and Markdown docs side by side, add anchored comments, and send feedback into an agent session or queue
- Model Registry — Manage providers (Anthropic, OpenAI, Google, DeepSeek, Ollama, LM Studio, MLX, and CLI subscription providers), compare pricing, switch models per session
- Session Insights — Analyze patterns across sessions to optimize prompts and workflows
Wall-E (Personal Digital Twin)
An always-on AI agent that learns from your Slack, email, calendar, and coding sessions.
- Second Brain — Automatically ingests your digital life and coding sessions into a searchable memory store with full-text search, knowledge extraction, and pattern detection
- Proactive Intelligence — Surfaces time-sensitive items, suggests actions, and delivers morning briefings and weekly reflections without being asked
- Chat with Tools — Talk to Wall-E in the browser — it can search memories, recall prior coding sessions, look up people, run skills, and call external tools via MCP
- 21 Bundled Skills — Morning briefing, weekly reflection, proactive alerts, Slack monitoring, email sync, calendar integration, coding agent, memory search, model training, model pricing sync, and more
- Multi-Model — Works with Claude, GPT, Gemini, DeepSeek, and local models via Ollama, LM Studio, or MLX with smart routing
- Skill Management GUI — Search, filter, create, edit, and monitor skills from the browser with rich cards, config forms, execution history, export/import, and pre-flight validation
- Multi-Device — Share your brain across machines via Dropbox or iCloud
Install
npx create-walle install ./walleThis copies the project, installs dependencies, auto-detects your name and timezone, and starts the server. Open http://localhost:3456 to finish setup in the browser, then pair your phone or tablet from Setup if you want remote access.
Download for Mac (no terminal)
Prefer a click-to-install app? Download the notarized Wall-E.app (Apple Silicon):
⬇ Download for Mac → Wall-E-…-arm64.dmg
Open the DMG, drag Wall-E to Applications, and launch it. First run installs everything into ~/.walle and opens the dashboard — Developer-ID notarized + stapled, so there's no Gatekeeper warning. Under the hood it runs the same create-walle setup.
Commands
npx create-walle install <dir> # Install CTM + Wall-E (or update if already installed)
npx create-walle update # Update to latest version, keep your config
npx create-walle start # Start as background service (auto-restarts on reboot)
npx create-walle stop # Stop the service
npx create-walle status # Check if running
npx create-walle logs # Tail the service logs
npx create-walle uninstall # Remove the auto-start service
npx create-walle -v # Show versionInstall, update, and start verify Node-native modules such as better-sqlite3
against the exact Node.js binary Wall-E will use. If you switch Node versions,
Wall-E automatically runs the needed npm rebuild before starting so CTM does
not crash with a NODE_MODULE_VERSION mismatch.
Pinning Node (optional — for machines with more than one Node)
On a machine with a single Node, the auto-rebuild above is all you need.
But if you have two or more Node versions (e.g. a system Node and a
Homebrew Node, or you switch with nvm/fnm), the daemon and a background skill
can run under different majors and fight over the one compiled better-sqlite3
binary — each rebuild flips its ABI and the other side crash-loops with
"MCP never became ready".
To stop that, lock CTM + Wall-E to one Node:
bash bin/pin-node.sh # pin to your current node version
bash bin/pin-node.sh 22.12.0 # …or an explicit version
bash bin/pin-node.sh --unpin # revert to the default (auto-rebuild) behaviorThis writes a .node-version so the launchers always resolve that exact Node
and the daemon refuses to start under a different major (with a clear message)
instead of silently corrupting the native binary. Existing installs adopt it the
moment you run the command — nothing else changes.
Setup
On first launch, the browser setup page guides you through:
- Owner name — auto-detected from
git config - API key — enter manually, or click "Auto-detect" to find it from your shell environment, Claude Code OAuth, or corporate devbox
- Integrations — connect Slack (OAuth), email and calendar auto-detected on macOS
- Remote phone and tablet access — optional QR pairing with Microsoft Dev Tunnels, Tailscale, Cloudflare Tunnel, or Walle Remote, including touch-friendly prompts and model controls
Custom Port
CTM_PORT=5000 npx create-walle install ./walleWall-E runs on CTM_PORT + 1 (e.g., 5001).
Architecture
Everything runs locally. CTM serves the dashboard, Wall-E runs as a background agent. Both use SQLite — no external databases, no cloud dependency beyond your LLM API keys.
| Component | Default Port | What it does | |-----------|-------------|--------------| | CTM | 3456 | Dashboard, multi-agent terminal, prompt editor, queue, model registry, code/doc review, remote phone/tablet UI | | Wall-E | 3457 | AI agent, brain database, skills engine, multi-model chat API |
Links
License
MIT
