Openclaw | Attack on Life

OpenClaw (Lobster) Implementing Social Media Image-Text Publishing

Wed, 11 Mar 2026 23:25:13 +0800

Lobster is quite popular, but it doesn’t produce any new technology itself. It simply provides mainstream IM tools with the capability to leverage AI. So I thought it could also solve the daily publishing workflow for social media creators.

Existing Skills

First, let me introduce some existing skills. You can directly ask your AI to install these, and you can ask the AI for usage instructions.

https://github.com/JimLiu/baoyu-skills/tree/main/skills Explanation: From Baoyu’s skills, I currently only use baoyu-cover-image (for generating article cover image prompts) and baoyu-post-to-wechat (for solving WeChat Official Account publishing issues).

For other platforms like Toutiao and Xiaohongshu, I’m currently developing them myself because they’re highly customized, so I won’t share them for now.

For platforms like Xiaohongshu and Toutiao, since they have PC web interfaces, you can use Playwright to simulate browser operations. Of course, you could also use API interfaces, but they’re too easily blocked. I personally recommend directly manipulating the web pages.
For WeChat Official Account, since there’s an official API, the aforementioned Skill recommends using the official API method for publishing, as it’s more stable. Of course, Baoyu’s skill is compatible with both API and non-API approaches. Without an API, it naturally falls back to browser page operations.

Compared to GPT and Gemini, Gemini is much more powerful. Chinese character rendering is now good without obvious issues. Since API pricing is a threshold issue and costs are a concern, I’m using the web-based solution directly. That is, using Playwright to simulate browser operations, generating images directly on the web page, and downloading them locally. This way, you can continue with image-text publishing.

Writing Skills

Although there are some solutions online, whether for security or customization reasons, you always end up needing to modify them. So how to write efficiently? Here’s my approach: I use the Chrome Claude plugin to write directly on the target page. This way, Claude helps generate the rough code and also verifies its effectiveness. Then I can copy the basic logic and have OpenClaw re-encapsulate it.

Final Thoughts

So far, the most critical image generation and publishing are sorted out. This actually saves considerable time, and it also makes it easy to do multi-platform simultaneous publishing. So, let’s get to it!

Hardware Requirements for Deploying Openclaw

Fri, 06 Mar 2026 17:48:36 +0800

A friend recently asked me: what kind of machine do you actually need to deploy OpenClaw (formerly ClawdBot)? Bottom line up front: it’s very lightweight, and hardware isn’t the bottleneck. A low-spec machine can run it, but whether you run it stably and fast depends on your specific use case.

OpenClaw Minimum Requirements

OpenClaw is officially positioned as “low barrier to deploy.” The following specs serve as a baseline:

CPU: 2+ cores (Intel N-series, entry-level AMD Ryzen, or ARM all work)
RAM: 4GB (basic chat functionality can go as low as 2GB)
Storage: At least 2GB free disk space
Runtime: Node.js v22+
OS: Linux, Windows (via WSL2), or macOS 13+
Network: Stable internet connection; if using overseas models, make sure your network can reach them

Recommended Specs

For more stable long-term operation:

RAM: 16GB or more
Storage: 256GB SSD (improves system responsiveness and I/O)
CPU: 4+ cores (better experience for concurrent tasks and browser automation)

The baseline gets you “can it run,” while the recommended specs determine “will it run without frequent freezes or disconnects.”

Deployment Options

1) Cloud

Budget VPS: Starting around $5/month; domestic cloud providers work too.
Free option: Oracle Cloud free tier (4 ARM cores + 24GB RAM available).

Best for:

24/7 availability
Not tying up your local machine

2) Local Deployment

Can use Docker
Or install Node.js directly on the host and run it; personally, I deploy on a Mac mini at home.

Best for:

Frequent debugging and development
Data locality requirements

When You Need More Power

OpenClaw itself is lightweight, but these scenarios significantly raise hardware demands:

Running local LLMs: At least 8GB–16GB RAM recommended
Browser automation enabled: 16GB RAM recommended for a stable experience
High concurrency (scraping + automation + chat simultaneously): Leave headroom in both CPU and RAM

Practical Advice

If you’re just trying it out, 2 cores + 4GB RAM + Node.js 22+ is enough to get started.

If you plan to run automation tasks long-term, go straight for 4 cores + 16GB + SSD — you’ll save a lot of troubleshooting and restart time down the road.

Also, the installation process typically supports a one-liner CLI command. Get it running first, then scale up based on actual load — that’s the most efficient approach.

How Openclaw Memory Works: Management and Invocation

Wed, 04 Mar 2026 22:10:12 +0800

I recently ran into an issue: I wanted both group chats and private chats with the bot to remember certain rules. When I went to implement it, I found my understanding of how “the lobster” handles memory was a bit off. Here’s a summary of how memory actually works.

Group Chat vs. Private Chat

First, whether it’s a group or a private chat, each is an independent Agent instance. This means their memory is not directly shared — each consumes its own context. Start with this mental model.

Memory Management

The official docs describe two memory file types. Pay attention to the time limits and the group/private distinction:

memory/YYYY-MM-DD.md
- Daily log (append-only)
- Today’s and yesterday’s logs are read at session start
MEMORY.md (optional)
- Curated long-term memory
- Only loaded in the main, private session (never in group contexts)

Truly Global Files (Global Memory)

SOUL.md — Who you are (personality / tone / values)
- Defines the assistant’s “character and style”
- Examples: speaking style, level of conciseness, attitude toward tasks
AGENTS.md — How you work (operations manual / behavioral rules)
- Defines workflows, boundaries, memory strategy, and safety habits
- Examples: which files to read first, when to ask vs. when not to share externally
TOOLS.md — Local notes for this specific environment (tool details)
- Environment-specific information, not general rules
- Examples: device names, account aliases, common commands, preferred settings

Note: all three files live in ~/.openclaw/workspace

Closing Thoughts

Part of what makes the lobster effective is prompt design — and prompts can themselves be understood as a form of AI memory. I’ll keep learning as I go.

https://docs.openclaw.ai/concepts/memory

OpenClaw MCP Setup Guide: How to Connect Third-Party Tools to Your AI Assistant

Wed, 04 Mar 2026 17:35:58 +0800

I needed to call TAPD MCP in OpenClaw, but found that it doesn’t natively support MCP. A third-party solution is required. The official recommendation is to use MCPorter as a middleware layer.

Install MCPorter

npm i mcporter


which uvx

curl -LsSf https://astral.sh/uv/install.sh | sh

source ~/.bashrc # or source ~/.profile

Add MCP

npx mcporter config add mcp-server-tapd
–stdio “uvx mcp-server-tapd”
–env TAPD_ACCESS_TOKEN=xxxx
–env TAPD_API_BASE_URL=https://api.tapd.cn
–env TAPD_BASE_URL=https://www.tapd.cn

The config file is located at /root/config/mcporter.json.

View

Run this command to check the MCP status:

mcporter list

OpenClaw Getting Started - installation, configuration, Telegram Bot integration, and MCP basics
OpenClaw Memory Management and Invocation - global memory via SOUL.md and AGENTS.md
OpenClaw for Social Media Publishing - using MCP to publish to WeChat, Xiaohongshu, and Toutiao

Usage

When using it, you can explicitly tell OpenClaw to use the mcp-server-tapd under MCPorter at the beginning. Once it’s saved to memory, you can simplify it afterward by just sending the ticket link directly.

Integrating Openclaw with WeCom (Enterprise WeChat)

Fri, 27 Feb 2026 21:47:39 +0800

At work we use WeCom (Enterprise WeChat), so I wanted to integrate Openclaw into it. For client-facing communication, regular WeChat is more common, but unfortunately WeChat itself doesn’t offer a bot mechanism. So for now I’m not considering external use — just internal efficiency first. WeCom does have both bot and app mechanisms, meaning you can configure various bots.

Installing Openclaw

This is still a one-liner — just make sure your Node version is 22+.

# nvm
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.4/install.sh | bash

# Install Openclaw
curl -fsSL https://openclaw.ai/install.sh | bash

Openclaw WeCom Plugin

Someone in the community has already contributed a plugin, so just use it directly. Note that the official Openclaw site doesn’t have WeCom integration docs yet — I saw a related PR but it hasn’t been merged. So for now, just follow the plugin’s instructions.

openclaw-wecom-plugin

# Install the plugin
openclaw plugins install @creatoraris/openclaw-wecom

Plugin Configuration

{
 "plugins": {
 "entries": {
 "openclaw-wecom": {
 "enabled": true,
 "config": {
 "token": "your_token",
 "encodingAESKey": "your_encoding_aes_key",
 "corpId": "your_corp_id", // optional
 "port": 8788 // Openclaw default port
 }
 }
 }
 }
}

Note: You need to restart Openclaw for config changes to take effect. Use openclaw gateway restart.

WeCom Bot / App

The token and other parameters in the config above need to be obtained after creating a bot or app in the WeCom admin console. Here are the steps:

You can create one directly within WeCom. But watch out — for example, if you try to create a bot under your company’s organization, you might get an error saying the callback URL must be an intranet domain. In other words, the bot address is restricted by the admin. Keep this in mind.
Fill in the required callback URL and bot information as needed.

Complex Deployment — One-Click Deploy?

The deployment above can be somewhat complex. If you don’t want to handle it yourself, consider some turnkey deployment options from Chinese cloud providers. They’re basic but functional. For example, Tencent Cloud, or Alibaba Cloud which offers similar products.

Pros and Cons of Bots

Here are the downsides of WeCom bots I’ve noticed so far:

No slash command support
No support for rich text like images — text only, which is quite limited.

On the plus side, bots can be added to group chats, making it convenient to interact with multiple bots in one group.

Pros and Cons of Apps

I haven’t had the need to use apps yet, but here’s what I’ve learned. The downside of apps is they can’t be added to groups — only direct messages. The upside is they support some rich text message formats like images. Also, you can connect WeChat to communicate with individual users via WeCom Admin Console -> My Enterprise -> WeChat Plugin -> Scan QR with personal WeChat. Give it a try if you’re interested.

Final Thoughts

Overall, using Openclaw with WeCom works, though the experience is just okay. The core really comes down to the AI model. I’d recommend connecting GPT, or at minimum try MiniMax. As for Tencent’s Yuanbao — not great. Lastly, neither WeCom bots nor apps support slash commands, which feels a bit behind. Hopefully future updates will address this.

How to Choose the Best AI Model for OpenClaw

Tue, 24 Feb 2026 23:16:32 +0800

I’ve been using OpenClaw for a few weeks now and I love it. It’s become part of my daily high-frequency workflow. As my usage grows, tokens get consumed quickly. After testing various AI models and services, here’s a summary of my current AI service combination along with their pros and cons for reference.

ChatGPT Plus
Claude Pro
MiniMax Coding Plan — Sign up here
- I’m on the 29 RMB/month plan, used mainly as a fallback.
- Using the referral code above gets you a 10% discount and Builder status.
- One extra advantage of MiniMax is that its plans include image and voice generation, which Claude and GPT don’t offer.

For specific pricing and payment details, search within this site for the relevant articles.

How I Use Them

GPT uses the Codex OAuth method. For the model, just go with the latest Codex model.
Claude Code isn’t officially supported, but since it’s a CLI tool, it can be used as a subagent — for example, I use it for writing articles.
MiniMax supports OAuth. For the model, just pick the latest MiniMax M2.7.
```
openclaw plugins enable minimax-portal-auth
```

So why did I ultimately choose these AI services? Because I tried several others but found drawbacks that made me give up on them. Here are a few examples.

How About Claude Models? ❌

The best option would be Claude’s Opus, but it’s too expensive, and API payment has a high barrier, so I gave up. Also, Claude Code doesn’t offer OAuth, so while you can use it via CLI, it can’t serve as OpenClaw’s base model.

How About DeepSeek Models? ❌

Compared to GPT, it performs poorly — stability is terrible. Currently I think it’s okay for single-task execution agents like translation, but for handling logic — such as acting as an agent dispatcher/manager — forget it, it’s just too weak. In actual use, it’s not as good as MiniMax.

OpenClaw Getting Started Guide — Installation, Telegram Bot setup, and MCP usage
OpenClaw Enterprise WeChat Integration — Full guide for WeChat Bot and app configuration
OpenClaw Deployment Hardware Requirements — Server configuration recommendations and performance requirements

Final Thoughts

All things considered, monthly AI spending comes to a few hundred RMB — not super expensive, but not cheap either. For me, it’s mainly about improving efficiency and saving time, so I find it acceptable. If better AI services emerge in the future, I’ll continue experimenting and adjusting my AI service combination to achieve a better experience and cost-effectiveness.

Playing with OpenClaw: Raise Your AI Lobster

Fri, 20 Feb 2026 09:25:50 +0800

Installation

npm install openclaw -g

# Uninstall
npm uninstall openclaw -g

macOS App?

If you want to use features like voice wake, you’ll need to install the official app separately. However, I personally found the app to be quite buggy — for example, its gateway conflicts with the CLI gateway — so I’ve given up on the app for now.

Upgrading

# For stability, upgrading to beta is not recommended — only for early adopters
openclaw update --channel beta

# Upgrade to the latest stable version
openclaw update

Gateway

Start the gateway:

openclaw gateway

openclaw gateway restart

openclaw gateway stop

# Check status
openclaw gateway status

Web UI Configuration

http://127.0.0.1:18789/config

Log Debugging

View logs:

cat /tmp/openclaw/openclaw-2026-02-19.log

openclaw logs --follow

# Overall status check
openclaw status

Telegram Bot

In my opinion, the most popular and useful IMs are Telegram and Discord. I currently use Telegram.

Get Your User ID

@userinfobot

Create a Bot

@BotFather

Your Telegram user id:xxxxx

Pairing code: xxxx

Ask the bot owner to approve with:
openclaw pairing approve telegram <code>

Chrome Extension

The extension needs to be installed manually:

# Install extension
openclaw browser extension install

# Extension status
openclaw browser status

Usage tips:

Set the profile to openclaw and manage it as a separate profile.
Run openclaw browser open https://x.com on first use to log in, enabling automation.
The extension is located at ~/.openclaw/browser/chrome-extension and must be loaded manually in Chrome.

The current extension approach has obvious drawbacks — the relay connection drops frequently and requires manually toggling it back on, which often makes remote operation impossible. Hopefully the team will improve this in the future. For this reason, I tend to use the Playwright approach instead.

Check Extension Info

http://127.0.0.1:18800/json/version

Installing Skills

You can install skills using natural language commands.

Configuring Multiple Models / Providers

There are times when your GPT quota runs out and you need to switch to DeepSeek or another model. It’s worth configuring multiple models/providers in advance — switching between them is very convenient.

Here’s an example of configuring Codex and DeepSeek. First, add the following to ~/.openclaw/openclaw.json:

"auth": {
 "profiles": {
 "openai-codex:default": {
 "provider": "openai-codex",
 "mode": "oauth"
 },
 "deepseek:default": {
 "provider": "deepseek",
 "mode": "api_key"
 }
 }
 },
"models": {
 "mode": "merge",
 "providers": {
 "deepseek": {
 "baseUrl": "https://api.deepseek.com/v1",
 "apiKey": "xxx",
 "api": "openai-completions",
 "models": [
 {
 "id": "deepseek-chat",
 "name": "deepseek-chat"
 }
 ]
 }
 }
 }

Multiple Agents

Running openclaw onboard from the CLI does not allow you to select multiple AI providers. So if your AI quota runs out and you want to switch services, the only option is to add another agent.

openclaw agents add work

openclaw agents delete work

openclaw agents list

Final Thoughts

There’s a lot to play with here — I’d recommend giving it a try. Raising your own AI lobster is actually pretty fun.