Grok Bot cloud PC hosts Claude Code; drive it from Mac or iPhone
At a glance
Builder moved Claude Code + repos off a lagging MacBook onto a Grok Bot cloud PC, sends tasks from Mac/iPhone via T3 Code, and locks access with Tailscale. Pattern: keep heavy agent loops on the bot machine; approve push/deploy locally. This workflow is listed under Grok-Bot, Claude-Code, remote-dev, HITL, devtools.
MIT Go daemon + git hook reviews every commit with the CLIs you already pay for—Codex, Claude Code, Cursor, OpenCode, and first-class Grok Build (grok / grok-build). Findings stay in a ledger until closed; agent hooks push open review IDs back into the session for /roborev-fix before context goes cold. Reviews stay on your machine.
Self Labs’ Agent Vault gives agents mock tokens for checkout and sign-in; real card numbers and passwords never reach the model. Caps, merchant allowlists, and per-purchase approval. Connect Grok Bot via MCP or Meta Muse via custom connector in ~2 minutes (also Claude Code, Hermes, Codex).
Chicago meetup template for Grok Bot: point it at a PR, a number, or all open PRs and get a read-only verdict (KEEP, FIX FIRST, or BULLSH*T) with evidence and the exact next step—merge or close only after you say yes. Template: https://x.ai/bot/xcRveN6wru8GradsusbkI
Ledger’s Agent Intent queue lets background agents (Grok Bot, Muse, Hermes, OpenClaw, Dots) prepare actions—e.g. Grok Bot watches an inbox and drafts an invoice payment—while you review asynchronously and physically confirm on a Ledger signer Secure Screen. Agents never hold signing keys; coding agents can use Agent Stack CLI/skills too.