Personal Assistant Setup

Building a personal assistant with CoderClaw

CoderClaw extends CoderClaw’s multi-channel gateway (WhatsApp + Telegram + Discord + iMessage) with distributed runtime capabilities and enhanced security. This guide covers the “personal assistant” setup: one dedicated WhatsApp number that behaves like your always-on agent.

⚠️ Safety first

You’re putting an agent in a position to:

• run commands on your machine (depending on your Pi tool setup)
• read/write files in your workspace
• send messages back out via WhatsApp/Telegram/Discord/Mattermost (plugin)

Start conservative:

• Always set channels.whatsapp.allowFrom (never run open-to-the-world on your personal Mac).
• Use a dedicated WhatsApp number for the assistant.
• Heartbeats now default to every 30 minutes. Disable until you trust the setup by setting agents.defaults.heartbeat.every: "0m".

Prerequisites

• CoderClaw installed and onboarded — see Getting Started if you haven’t done this yet
• A second phone number (SIM/eSIM/prepaid) for the assistant

The two-phone setup (recommended)

You want this:

flowchart TB
    A["<b>Your Phone (personal)<br></b><br>Your WhatsApp<br>+1-555-YOU"] -- message --> B["<b>Second Phone (assistant)<br></b><br>Assistant WA<br>+1-555-ASSIST"]
    B -- linked via QR --> C["<b>Your Mac (coderclaw)<br></b><br>Pi agent"]

If you link your personal WhatsApp to CoderClaw, every message to you becomes “agent input”. That’s rarely what you want.

5-minute quick start

1. Pair WhatsApp Web (shows QR; scan with the assistant phone):

coderclaw channels login

2. Start the Gateway (leave it running):

coderclaw gateway --port 18789

3. Put a minimal config in ~/.coderclaw/coderclaw.json:

{
  channels: { whatsapp: { allowFrom: ["+15555550123"] } },
}

Now message the assistant number from your allowlisted phone.

When onboarding finishes, we auto-open the dashboard and print a clean (non-tokenized) link. If it prompts for auth, paste the token from gateway.auth.token into Control UI settings. To reopen later: coderclaw dashboard.

Give the agent a workspace (AGENTS)

CoderClaw reads operating instructions and “memory” from its workspace directory.

By default, CoderClaw uses ~/.coderclaw/workspace as the agent workspace, and will create it (plus starter AGENTS.md, SOUL.md, TOOLS.md, IDENTITY.md, USER.md, HEARTBEAT.md) automatically on setup/first agent run. BOOTSTRAP.md is only created when the workspace is brand new (it should not come back after you delete it). MEMORY.md is optional (not auto-created); when present, it is loaded for normal sessions. Subagent sessions only inject AGENTS.md and TOOLS.md.

Tip: treat this folder like CoderClaw’s “memory” and make it a git repo (ideally private) so your AGENTS.md + memory files are backed up. If git is installed, brand-new workspaces are auto-initialized.

coderclaw setup

Full workspace layout + backup guide: Agent workspace Memory workflow: Memory

Optional: choose a different workspace with agents.defaults.workspace (supports ~).

{
  agent: {
    workspace: "~/.coderclaw/workspace",
  },
}

If you already ship your own workspace files from a repo, you can disable bootstrap file creation entirely:

{
  agent: {
    skipBootstrap: true,
  },
}

The config that turns it into “an assistant”

CoderClaw defaults to a good assistant setup, but you’ll usually want to tune:

• persona/instructions in SOUL.md
• thinking defaults (if desired)
• heartbeats (once you trust it)

Example:

{
  logging: { level: "info" },
  agent: {
    model: "anthropic/claude-opus-4-6",
    workspace: "~/.coderclaw/workspace",
    thinkingDefault: "high",
    timeoutSeconds: 1800,
    // Start with 0; enable later.
    heartbeat: { every: "0m" },
  },
  channels: {
    whatsapp: {
      allowFrom: ["+15555550123"],
      groups: {
        "*": { requireMention: true },
      },
    },
  },
  routing: {
    groupChat: {
      mentionPatterns: ["@coderclaw", "coderclaw"],
    },
  },
  session: {
    scope: "per-sender",
    resetTriggers: ["/new", "/reset"],
    reset: {
      mode: "daily",
      atHour: 4,
      idleMinutes: 10080,
    },
  },
}

Sessions and memory

• Session files: ~/.coderclaw/agents/<agentId>/sessions/{{SessionId}}.jsonl
• Session metadata (token usage, last route, etc): ~/.coderclaw/agents/<agentId>/sessions/sessions.json (legacy: ~/.coderclaw/sessions/sessions.json)
• /new or /reset starts a fresh session for that chat (configurable via resetTriggers). If sent alone, the agent replies with a short hello to confirm the reset.
• /compact [instructions] compacts the session context and reports the remaining context budget.

Heartbeats (proactive mode)

By default, CoderClaw runs a heartbeat every 30 minutes with the prompt: Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK. Set agents.defaults.heartbeat.every: "0m" to disable.

• If HEARTBEAT.md exists but is effectively empty (only blank lines and markdown headers like # Heading), CoderClaw skips the heartbeat run to save API calls.
• If the file is missing, the heartbeat still runs and the model decides what to do.
• If the agent replies with HEARTBEAT_OK (optionally with short padding; see agents.defaults.heartbeat.ackMaxChars), CoderClaw suppresses outbound delivery for that heartbeat.
• Heartbeats run full agent turns — shorter intervals burn more tokens.

{
  agent: {
    heartbeat: { every: "30m" },
  },
}

Media in and out

Inbound attachments (images/audio/docs) can be surfaced to your command via templates:

• {{MediaPath}} (local temp file path)
• {{MediaUrl}} (pseudo-URL)
• {{Transcript}} (if audio transcription is enabled)

Outbound attachments from the agent: include MEDIA:<path-or-url> on its own line (no spaces). Example:

Here’s the screenshot.
MEDIA:https://example.com/screenshot.png

CoderClaw extracts these and sends them as media alongside the text.

Operations checklist

coderclaw status          # local status (creds, sessions, queued events)
coderclaw status --all    # full diagnosis (read-only, pasteable)
coderclaw status --deep   # adds gateway health probes (Telegram + Discord)
coderclaw health --json   # gateway health snapshot (WS)

Logs live under /tmp/coderclaw/ (default: coderclaw-YYYY-MM-DD.log).

Next steps

• CoderClaw Phase 2 Features: Phase 2 Documentation
• WebChat: WebChat
• Gateway ops: Gateway runbook
• Cron + wakeups: Cron jobs
• macOS menu bar companion: CoderClaw macOS app
• iOS node app: iOS app
• Android node app: Android app
• Windows status: Windows (WSL2)
• Linux status: Linux app
• Security: Security