Tools
Go From Setup to Production-Ready Read the original with full formatting → OpenClaw is the open-source AI gateway that lets you run a personal AI assistant on your own infrastructure. It connects to any major LLM provider — Anthropic, OpenAI, Google, MiniMax — and pipes everything through your messaging apps: Telegram, Discord, WhatsApp, Signal. The result is an AI assistant that remembers who you are, runs 24/7, and does whatever you teach it to do. No subscription to someone else's platform. No data leaving your server unless you decide it should. This guide walks you through the complete setup. By the end, you will have a working OpenClaw agent responding to messages in Telegram. Which LLM should you start with? For best quality, go with Anthropic Claude. For free, MiniMax M2.5 has a generous free tier with a 200K context window. You can always switch or add more providers later — OpenClaw supports multiple simultaneously. First, verify your Node.js version: If you need to install or update Node.js: Now install OpenClaw globally: Run the onboarding wizard — this handles initial configuration and sets up the background daemon: The onboarding walks you through creating your workspace, setting up the gateway service, and configuring your first LLM provider. Once complete, verify everything is running: OpenClaw needs at least one AI provider. Open your configuration file at ~/.openclaw/openclaw.json and add your provider credentials: Security note: Never commit API keys to version control. For production setups, use a separate secrets.env file with restricted permissions (chmod 600). The OpenClaw Field Guide covers proper secrets management in detail. Set your default model in the same config: Restart the gateway to pick up changes: Telegram is the fastest channel to configure. Here is the process: That is it. You now have a working AI assistant on Telegram. But it is a blank slate — it does not know who it is or what it should do. That is where workspace files come in. OpenClaw's workspace is a directory of files that your agent reads at the start of every conversation. This is what makes it fundamentally different from ChatGPT or a basic API wrapper — your agent has persistent, editable context. Navigate to your workspace: This file defines personality, voice, and behavioral rules: Also create the daily memory directory: Restart one more time to load everything: Send your bot another message. It should respond with the personality you defined. The heartbeat system lets your agent check in periodically and do background work. Create HEARTBEAT.md in your workspace: Cron jobs run tasks on a schedule: Each of these topics could fill its own article. But if you want the complete picture in one place, organized and tested against real production deployments, that is exactly what we built the Field Guide for. The OpenClaw Field Guide is 58 pages across 14 chapters of exactly this — setup, configuration, skill routing, memory architecture, cron automation, and multi-agent delegation. Everything you need to go from installed to indispensable. If you found this useful, check out the OpenClaw Field Guide — a 58-page manual for setting up your own personal AI assistant on a VPS. Templates let you quickly answer FAQs or store snippets for re-use. Hide child comments as well For further actions, you may consider blocking this person and/or reporting abuse
Tools: How to Set Up OpenClaw in 30 Minutes (Complete 2026 Guide)
What You Need
Phase 1: Install OpenClaw (5 minutes)
Troubleshooting: Gateway Won't Start
Phase 2: Add Your LLM Provider (5 minutes)
Option A: Anthropic (Claude)
Option B: OpenAI (GPT)
Option C: MiniMax (Free Tier)
Phase 3: Connect Telegram (5 minutes)
Phase 4: Give Your Agent a Brain (10 minutes)
SOUL.md — Who Your Agent Is
USER.md — Who You Are
MEMORY.md — Long-Term Memory
Phase 5: Make It Useful (5 minutes)
Add a Heartbeat
Add a Cron Job
What You Should Have Now
Your 30-Minute Checklist — Complete
Where to Go From Here
Go From Setup to Production-Ready Read the original with full formatting → OpenClaw is the open-source AI gateway that lets you run a personal AI assistant on your own infrastructure. It connects to any major LLM provider — Anthropic, OpenAI, Google, MiniMax — and pipes everything through your messaging apps: Telegram, Discord, WhatsApp, Signal. The result is an AI assistant that remembers who you are, runs 24/7, and does whatever you teach it to do. No subscription to someone else's platform. No data leaving your server unless you decide it should. This guide walks you through the complete setup. By the end, you will have a working OpenClaw agent responding to messages in Telegram. Which LLM should you start with? For best quality, go with Anthropic Claude. For free, MiniMax M2.5 has a generous free tier with a 200K context window. You can always switch or add more providers later — OpenClaw supports multiple simultaneously. First, verify your Node.js version: If you need to install or update Node.js: Now install OpenClaw globally: Run the onboarding wizard — this handles initial configuration and sets up the background daemon: The onboarding walks you through creating your workspace, setting up the gateway service, and configuring your first LLM provider. Once complete, verify everything is running: OpenClaw needs at least one AI provider. Open your configuration file at ~/.openclaw/openclaw.json and add your provider credentials: Security note: Never commit API keys to version control. For production setups, use a separate secrets.env file with restricted permissions (chmod 600). The OpenClaw Field Guide covers proper secrets management in detail. Set your default model in the same config: Restart the gateway to pick up changes: Telegram is the fastest channel to configure. Here is the process: That is it. You now have a working AI assistant on Telegram. But it is a blank slate — it does not know who it is or what it should do. That is where workspace files come in. OpenClaw's workspace is a directory of files that your agent reads at the start of every conversation. This is what makes it fundamentally different from ChatGPT or a basic API wrapper — your agent has persistent, editable context. Navigate to your workspace: This file defines personality, voice, and behavioral rules: Also create the daily memory directory: Restart one more time to load everything: Send your bot another message. It should respond with the personality you defined. The heartbeat system lets your agent check in periodically and do background work. Create HEARTBEAT.md in your workspace: Cron jobs run tasks on a schedule: Each of these topics could fill its own article. But if you want the complete picture in one place, organized and tested against real production deployments, that is exactly what we built the Field Guide for. The OpenClaw Field Guide is 58 pages across 14 chapters of exactly this — setup, configuration, skill routing, memory architecture, cron automation, and multi-agent delegation. Everything you need to go from installed to indispensable. If you found this useful, check out the OpenClaw Field Guide — a 58-page manual for setting up your own personal AI assistant on a VPS. Templates let you quickly answer FAQs or store snippets for re-use. Hide child comments as well For further actions, you may consider blocking this person and/or reporting abuseKey Facts
- [Important context your agent should always remember]
Decisions
- [Track decisions so your agent does not re-litigate them]`
Key Facts
- [Important context your agent should always remember]
Decisions
- [Track decisions so your agent does not re-litigate them]`
Key Facts
- [Important context your agent should always remember]
Decisions
- [Track decisions so your agent does not re-litigate them]`