Run Claude Code, Codex, Gemini, Aider, OpenCode, and Cursor Agent sessions side by side. Manage prompts, queue tasks, open a phone-friendly remote UI, and let an AI agent build a second brain from your work life.
npx create-walle install ./walle
click to copy
$ npx create-walle install ./walle Installing CTM + Wall-E... Auto-detected owner: Your Name Auto-detected timezone: America/Los_Angeles Installing dependencies... done CTM running at http://localhost:3456 Wall-E running at http://localhost:3457 Open your browser to finish setup.
Run Claude Code, Codex, Gemini CLI, and Aider sessions side by side. Manage prompts, queue tasks, review code, and respond from your phone.
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.
Save, version, and organize prompts with folders, tags, chains, templates, variables, and full-text search.
Queue prompts for sequential execution. Auto-advance when the agent finishes, or step through manually with approval gates.
Auto-approve tool-use requests based on learned rules. Uncertain cases escalate to you. Builds trust over time.
Pair your phone with a QR code and use a mobile CTM UI through Microsoft Dev Tunnels, Tailscale, Cloudflare Tunnel, or Walle Remote.
View git diffs from any project — staged, unstaged, or between branches — with line-level detail in a clean split view.
Wall-E runs in the background, ingesting your digital life into a searchable memory store. Ask it anything.
Automatically ingests Slack, email, calendar, and coding sessions into searchable memory with knowledge extraction and pattern detection.
Surfaces time-sensitive items, suggests actions, and delivers morning briefings and weekly reflections without being asked.
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.
Morning briefing, Slack monitoring, email sync, calendar integration, coding agent, memory search, model training, model pricing sync, and more — all configurable from the UI.
Works with Claude, GPT, Gemini, DeepSeek, and local models via Ollama, LM Studio, or MLX. Smart routing picks the best model for each task.
Share your brain across machines via Dropbox, iCloud, or any file sync. Pair your phone when you need to monitor or respond away from the Mac.
No Docker, no cloud accounts, no config files. Just Node.js and an API key.
npx create-walle install ./walle
Copies the project, installs deps, and starts the server.
Navigate to localhost:3456. The setup wizard auto-detects your name, timezone, and API key.
Click through to connect Slack (OAuth), email, and calendar. All optional — Wall-E works without them.
Choose Microsoft Dev Tunnels, Tailscale, Cloudflare Tunnel, or Walle Remote from Setup and scan the QR code.
Launch coding sessions, queue prompts, and let Wall-E learn from your work in the background.
Two lightweight Node.js processes and SQLite. No external databases, no cloud dependency beyond your LLM API keys.