This is usopenclaw teachingFirst one, you can code first, then three to five more, and then you can use it at the top
First, let's get this straight OpenClaw What is it
OpenClaw is essentially a locally run AI gateway
Its structure is simple:
{\cHFFFFFF}{\cH00FFFF} Your computer runs a Gateway process {\cHFFFFFF}{\cH00FFFF} {\cHFFFFFF}{\cH00FFFF} {\cHFFFFFF}{\cH00FFFF} {\cHFFFFFF}{\cH00FFFF} {\cHFFFFFF} Gateway {\cHFFFFFF}{\cH00FFFF} {\cHFFFFFF}{\cH00FF00} {\cHFFFFFF}{\cH00FF00} {\cHFFFFFF}{\cH00FF00} {\cHFFFFFF}{\cH00FF00} {\cHFFFFFF}{\cH00FF00} {\cHFFFFFF} {\cHFFFF00} You send a Gateway to AI \AI \AI \AIgram
Why would you do that
Because most of the AI services (Claude, GPT) do not directly provide Telegram robots, you use either the web version or the App
But OpenClaw allows you to talk to AI in any chat software, and all memories and configurations are on your own computer (~/.openclaw/), without risk of privacy disclosure
Second, get ready for the prep
1. Hardware and system requirements
Mac Users: Best Saved, Native Support MacOSWindows Users: WSL2 (Windows Subsystem for Linux) strongly recommends Ubuntu 22.04Linux Users: Directly
If you want to hang up 24 hours, suggest:
- Mac Mini (most electricity, official recommendation)
- Cloud Server VPS (Digital Ocean 12 US$/month, Hostinger is also available and domestic)
2. LARGE MODEL API READINESS
OpenClaw supports almost all mainstream models, but you need to be ready in advance
Comparison of recommended programmes:
ChatGPT Plus Subscription
$20/MONTH, OFFICIAL WHITE LIST SUPPORTED, MOST ECONOMICAL
Coding Plan
Qwen3-Max/kimi k2.5
OpenRouter (⭐⭐⭐⭐)
BASED ON VOLUME, APPROXIMATELY $3-15/DAY, MULTI-MODEL SWITCHING, SUITABLE FOR TESTING
AI/ML API (⭐⭐⭐⭐)
Pays in volume, supports multiple models, OpenClaw official integrated partners
Kimi K2.5 (⭐⭐⭐⭐)
Pays by volume, and the dark side of the moon actively supports OpenClaw
Transit stations (⭐⭐⭐)
Cheap but unstable, high risk
Ollama Local Model
It's completely free, cost-free, but not effective, suitable for learning
My suggestions:
- Start with OpenRouter or AI/ML API, pay in volume, don't waste
- make sure it's a long-term one
- Don't get up to the stop. You don't know if it's a model or a configuration
3. Wallbreaking environment (important)
Telegram and Discord both need to cross the wall to connect
You need:
- Clash Verge / Clash for Windows / Surge
- A stable airport node
- TURN ON TUN MODE (MANY PEOPLE FORGET, DON'T OPEN TUN MODE, TERMINAL CANNOT WALK AGENT)
Validation method:
i can't believe it
If returned 200, indicate that your terminal can access Telegram API
The official installation will follow you
Step 1: Install Homebrew and Node.js
Open Terminal with Homebrew:
/bin/bash -c "$(curl-fsSL)"
https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh
Node.js:
i'm going to tell you something
Validation installation:
node –version # should show v22.x.x or higher
npm -version
Important: OpenClaw requires Node.js version 22, less than this version will be wrong
Step 2: Install OpenClaw
Recommended mode (official guide):
quil-fssL bash https://openclaw.ai/install.sh
This script will automatically help you:
- Install OpenClaw CLI tool
- create profile directory (~/.openclaw/)
- Set Environment Variable
Once installed, run:
openclaw -version
Seeing the version number means it's loaded
Step 3: Start Configuration Wizard
This is the most critical step:
this is an openclaw on board-install-daemon
–install-daemon parameters allow OpenClaw to continue in the backstage, even if the computer is restarted
And then you're going to go into an interactive wizard, in a few steps:
IV. The configuration process is where most people are stuck
4.1 SELECTION OF AI MODEL PROVIDER
The wizard lists:
- OpenAI (GPT)
- i'm sorry
- I don't know.
- Skip
If you have an official account number: select the corresponding one, then jump through the browser
If you use a third party API (OpenRouter, Transit etc.): Choose Skip
After skipping, the wizard will continue
4.2 Select Chat Platform
The wizard will ask which platform you want to connect to:
• Telegram (Bot API)
Whatsapp (QR code)
° Discord (Bot API)
Skip
Why recommend Telegram:
- The simplest configuration (three minutes done)
- Bot creation without review
- Support long message and file transfer
- Full Bot Management Panel
Discord for whom:
- There already is a team of Discord servers
- It takes a lot of people to work with
- Configure time approximately 10 minutes [7]
Here we go first, Telegram
4.3 Create Telegram Bot
Open Telegram, search @BotFather
send /start start dialogue
Then send in order:
- /newbot
- Enter your Bot display name (e. g. my AI assistant)
- Enter Bot username (must end with _bot, e. g. ai_bot)
After success, BotFather returns a Token format similar to:
1234567890: ABCdefGHIjklMNOpqrsTUVwxyz
Copy this TokenBack to the terminal. Paste in
4.4 Completion of initial configuration
The wizard will ask if you want to install Skills, for example:
- Web Search
- Mail Management
- Organisation
- File Operations
The new guy suggested we skip first, wait for the basics to go through
After the configuration is completed, the Wizard will automatically start Gateway:
• Gateway started on http://127.0.0.1:18789
Telegram channel conned
Ready to chat!
CONFIGURE THIRD-PARTY AI MODELS
If you choose Skip in 4.1, now you need a manual configuration model (the following steps strongly recommend cursor and so on to be an assistant
Method 1: Through Web UI Configuration (Recommended)
Open browser, access:
http://127.0.0.1:18789
This is OpenClaw's control panel
Click Settlings →Models →Add Projecter
FILL IN YOUR API MESSAGE:
- Provider Name: Custom (e. g. openrouter)
- Base URL: Your API address
- Your key
- Model ID: Specific model name (e.g. claude-opus-4)
After saving, texting test for Bot in Telegram
Method 2: Directly edit configuration files
Open profile:
~/.openclaw/openclaw.json
found models.providers section, add:
{“Models”: {“providers”: {“openrouter”: {“baseUrl”: “https://openrouter.ai/api/v1”, “apiKey”: “your-api-key-here”, “api”: “openai-complements”, “models”: [{id”: “anthropic/claude-opus-4”, “name”: “Claude Opus 4”, “reasing”: True}}, “agents”:}, {“defaults”: {model: {primary”: {openrouter/antrope-opus-4}}
Start again after saving
openclaw present
METHOD 3: USE AI/ML API (OFFICIAL INTEGRATION)
IF YOU USE AI/ML API, YOU CAN USE THEIR SPECIAL VERSIONS DIRECTLY WHEN INSTALLED:
@latest
This version will automatically configure the AI/ML API Skills
VI. CONFIGURE THE NETWORK AGENT SO THAT YOUR AI CAN ACCESS THE NETWORK
Bot didn't get back
Confirm your proxy port
Open Clash Verge, see:
- HTTP PORT (GENERALLY 7890)
- SOCKS5 PORT (GENERALLY 7891)
Set Environment Variable
edit shell profile:
# if with zsh (Mac Default)
~ /.zshrc
# if use bash
~/.bahrc
Add at the end of the document:
export http_proxy=http://127.0.0.1:7890
export https_proxy=http://127.0.0.1:7890
for example, all_proxy=socks5://127.0.0.1:7891
Save and reload:
~/.zshrc # or ~/.bashrc
Restart OpenClaw:
openclaw present
Validation agent:
Message to Bot in Telegram: Search OpenClaw for updates
If you can return the result, indicate that the agent's configuration is successful
VII. PROGRESS CONFIGURATION MAKES AI REALLY USEFUL
7.1 CONFIGURE PERSONALISED SOUL
OpenClaw supports custom AI character and behaviour rules
Edit files:
nono~/.openlaw/workspace/SOUL.md
Write your requests, for example:
# MY IAA ASSISTANT PERSONALISATION - CALL ME "BOSS" - RESPONDS STYLE: SIMPLICITY, NO BULLSHIT - EXPERTISE IN THE FIELD: PRODUCT DESIGN, TECHNICAL STRUCTURES, CONTENT CREATION - BAN: DON'T ACTIVE TALK, DON'T SAY "SORRY" THAT'S THE KIND OF TALK
ONCE SAVED, AI WILL RETURN TO YOU WITH THIS SETUP
7.2 Security configuration (this must be done)
OpenClaw was warned by a safety researcher about the risks because of the overload
Security measures that must be put in place:
- Limit API spending caps on your API provider backstage (OpenRouter/Claude etc.) to a daily/monthly budget cap
- enable sensitive operation to confirm edit configuration file, find tables section:
{“tools”: {“exec”: {enabled”: true, “approval Required”: true / / / need your confirmation before executing the command}, “email”: {enabled”: true, “approval Required”: true / / e-mail requires your confirmation }
- OpenClaw is not exposed to the public web Gateway default listening 127.0.0.1:18789, only in-house access, and never change to 0.0.0.0
VIII. CLASSING ISSUES
Question 1: Bot doesn't reply
Quest steps:
# 1. Check whether Gateway is running openclaw status
# 2. View logbooks
# 3. Test model connection openclaw anent –message "test" -thining high
If logs see ECONNREFUSED or timeout, it's a web-based proxy problem
If you see 401 Unauthorized, it's API Key error
If you see arate limitt, it's your API level
Question 2: Port occupied
Error: listen EADDRINUE: address already in use #18789
Resolve:
# PROCESS OF FINDING PORT OF OCCUPATION
lsof-i:18789
# KILL PROCESS (PID IS THE LAST AVAILABLE NUMBER)
you know, kill-9 on the ped
# Restart OpenClaw
openclaw present
</pid>
Question 3: Telegram pair failed
If Bot creates but does not match:
# VIEW PAIRING
openclaw calling list
# MANUAL APPROVAL PAIR
your Telegram User ID
Your User ID can be retrieved from Telegram@userinfobot
IX. COSTS AND POSITION RECOMMENDATIONS
We'll talk about the cost
Minimum cost scenario(approximately 30 yuan/month):
- Ollama Local Model
- Telegram
- My own computer is on 24 hours a day
- Total: 20-30 yuan/month
Price-for-money scheme(approximately 150 yuan/month):
- OpenRouter Pays by Volume (approximately $100/month, light)
- Telegram (free of charge)
- CLOUD SERVER VPS (APPROXIMATELY 50 YUAN/MONTH)
- Total: 150 yuan/month
The Too programme(approximately $1,000 per month):
- direct to claude api
- Mac Mini local running (one-time input of $3000)
- Total: First month 4000+, follow-up 1000+/month
My advice: run for a week or two, make sure you really use it, and then think about promotion
It's written at the end
OpenClaw's core value is not another AI chat tool
It's to shorten the process of "open the browser to log in and copy the results" to "send a message at Telegram"
This is the productivity tool that super-individuals need: seamless, ready, continuous memory
But it's not all-powerful either. Current problems include:
- It's too fast to update
- Skills, of mixed quality, some with security risks
- Configure complexity is not very friendly to white
But none of this prevents it from becoming the most promising open source project in 2026
If you have problems, don't give up
Claude Code or GitHub in OpenClaw
THE TECHNOLOGY IS ALWAYS FOR PEOPLE