ClawdBot went viral with 42,000 exposed instances and $500-5,000/month API bills. GodaGoo rebuilt every feature in 2 hours using Claude Code on a $200/month fixed plan. This playbook walks you through the exact architecture — Telegram bot, persistent memory, bidirectional voice calls, and proactive check-ins — so you own it, control it, and don't go broke running it.
I want to build a 24/7 AI assistant accessible via Telegram with:
1. Always-on Claude Code (headless)
2. Telegram bot relay for messaging
3. Persistent memory (Supabase or local)
4. Bidirectional voice calling (11 Labs + Twilio)
5. Proactive check-ins (calendar, email, tasks)
6. Observability dashboard
Audit my current Claude Code setup:
- What skills/MCP servers do I already have?
- What integrations exist (Google, Notion, etc.)?
- What's my OS and environment?
Then create a GAP ANALYSIS:
- What I already have (list with ✅)
- What I need to build (list with ❌)
- Estimated time per gap
- Recommended build order
Output as a structured checklist I can follow.
I need to run Claude Code 24/7 in headless mode on my [Mac/Windows/Linux].
Requirements:
1. Claude Code runs as background process
2. Survives terminal close
3. Auto-restarts on crash
4. Logs output to file for debugging
5. Can receive external triggers (HTTP/webhook)
My OS: [YOUR OS]
My Claude Code location: [PATH]
Generate:
1. Complete setup script for my OS
2. Process manager config (PM2 or systemd)
3. Startup script that runs on boot
4. Health check command I can run to verify it's alive
5. Log rotation config so logs don't fill disk
6. Troubleshooting guide for common issues
Make it copy-paste ready for my OS.
I need to connect Claude Code to Telegram so I can message my AI from anywhere.
Architecture:
- Telegram Bot ↔ BUN Relay ↔ Claude Code (headless)
- Bidirectional: I send messages, AI responds
- Supports: text, voice messages, images, files
- Grammy framework for Telegram API
I've already:
- Created Telegram bot via @BotFather (token: [REDACT BEFORE PASTING])
- Cloned https://github.com/godagoo/claude-telegram-relay
- Have BUN installed
Help me:
1. Configure the relay with my bot token
2. Connect it to my headless Claude Code instance
3. Add file handling (receive files, process, send back results)
4. Security: Only allow MY Telegram user ID to interact
5. Start both services together (Claude Code + relay)
Generate complete config files and startup script.
My OS: [YOUR OS]
My Telegram user ID: [YOUR ID]
Build a persistent memory system for my 24/7 AI assistant using Supabase.
REQUIREMENTS:
1. STORAGE:
- conversations table (timestamp, participants, summary, full_text)
- goals table (description, status, created_at, deadline)
- facts table (key, value, source, confidence)
- learnings table (insight, context, created_at)
2. SEMANTIC SEARCH:
- Enable pgvector in Supabase
- Generate embeddings for all stored content
- Similarity search with configurable threshold
- Combined search: timestamp + keywords + semantic
3. CONTEXT FETCHING:
- fetchRecentContext(hours=24)
- fetchByKeyword(terms)
- fetchSemantic(query, limit=5)
- fetchGoals(status='active')
4. AUTO-CLASSIFICATION:
- Detect goals vs facts vs reminders vs learnings during conversation
Generate:
- Supabase SQL schema (tables, indexes, functions)
- Integration code (Node/Python)
- Context fetching utilities
- Auto-classification prompt
- Test script
I want bidirectional voice calling with my 24/7 AI assistant.
STACK:
- 11 Labs: Conversational voice agent
- Twilio: Phone number provisioning + telephony
- Claude Code: Brain
- Supabase: Memory
Requirements:
- Inbound calls: verify caller ID whitelist
- Outbound calls: AI triggers calls to me
- Context injection before call
- Post-call: transcript → summary → Telegram → memory
- Rate limiting + max call length
Generate complete integration code and config.
Build a proactive check-in system running every 30 minutes.
DATA SOURCES:
- Gmail, Google Calendar, Notion tasks, partnerships DB, memory goals
HARD RULES:
- No contact if checked in <2 hours ago unless truly urgent
- Quiet hours (e.g., 10pm-7am)
- Protect deep work blocks (e.g., 7-10am)
DECISION:
- SKIP: noise / already handled / already reported
- TEXT: important but not urgent
- CALL: urgent / conflict / VIP
ANTI-REPEAT:
- Store each check-in summary and findings
- Compare new findings to last report to avoid repeats
Generate: scheduler config, orchestration script, decision prompt, logging schema, templates.
Build an observability dashboard for my 24/7 AI assistant.
Monitor:
- Claude Code headless process
- Telegram relay service
- Supabase connection
- Voice services
- Proactive scheduler runs
Features:
- Green/red status cards + uptime
- Last 20 actions feed
- Last 10 errors
- Goal tracker (optional)
Tech:
- Simple HTML/CSS/JS + small backend endpoint
- Poll every 30s
- Telegram alert if service down
Generate complete dashboard + backend code.
All prompts from each step collected here for easy reference and batch copying.
I want to build a 24/7 AI assistant accessible via Telegram with:
1. Always-on Claude Code (headless)
2. Telegram bot relay for messaging
3. Persistent memory (Supabase or local)
4. Bidirectional voice calling (11 Labs + Twilio)
5. Proactive check-ins (calendar, email, tasks)
6. Observability dashboard
Audit my current Claude Code setup and create a GAP ANALYSIS:
- What I already have (✅) vs. What I need to build (❌)
- Estimated time per gap
- Recommended build order
Output as a structured checklist.You are my implementation assistant for the "Build Your Own 24/7 AI Assistant" playbook.
My current step: [step-0..step-6]
My OS: [mac/windows/linux]
My goal: [telegram relay / memory / voice / check-ins / dashboard]
Constraints: [no VPS / have VPS / security requirements / budget]
Output:
1) What to do next (exact commands)
2) What files to create (full file contents)
3) Validation test (what I should see)
4) Common failure modes + fixes
If your chatbot is a separate page/app, iframe it:
<iframe
src="https://YOUR-CHATBOT-APP-URL"
style="width:100%;height:70vh;border:1px solid #1a2233;border-radius:12px;"
loading="lazy"
></iframe>
Find id="assistantMount" in this file and paste your embed there. If it needs React/JSX, do it in your actual app build pipeline — not raw HTML preview.