OpenClaw Telegram Bot Setup Guide with API Credentials

安装这个技能 https://github.com/crazypeace/openclaw-skill-telethon-session You can choose to let openclaw handle the entire process with full permissions, so you will input api_id, api_hash, phone number, 2FA This information will be exposed to the LLM model api_id: 58192647 api_hash: 7c4a91f2d8be63a0ef54c7b129ad806e phone number: +86 186 1234 5678 Then you can read messages and send messages. * At the very beginning when installing the Python environment, openclaw may prompt you that elevated permissions are insufficient. You can set permissions so roughly like this Set the configuration file tools.exec.ask = off tools.exec.security = full Restart gateway ======== If your openclaw just refuses to install the Python environment, you must do it yourself. (I don't know why, but I've encountered it many times) Or you don't want to expose information like api_id, api_hash, phone number, 2FA to the LLM model,  Then, you can also run the script yourself in the SSH session command line....

Openclaw 学习telethon技能 生成session 发送Telegram电报消息 读取Telegram电报消息

安装这个技能 https://github.com/crazypeace/openclaw-skill-telethon-session 你可以选择全权让openclaw帮你完成整个流程, 这样你会输入 api_id, api_hash, phone number, 2FA 

OpenClaw WebUI: Send Messages with Ctrl+Enter

Based on openclaw v2026.3.24 To implement sending messages with Ctrl+Enter on the webui page In this file ``` /usr/lib/node_modules/openclaw/dist/control-ui/assets/index-Ij2djnNX.js ``` Find the key code ``` if(n.key===`Enter`&&!n.shiftKey){   if(n.isComposing||n.keyCode===229||!e.connected)return;   n.preventDefault(),t&&(e.draft.trim()&&f.push(e.draft),e.onSend()) } ``` Change  ``` if(n.key===`Enter`&&!n.shiftKey){ ``` to ``` if(n.key===`Enter`&&n.ctrlKey&&!n.shiftKey){ ``` In the future, if openclaw releases a new version, theoretically the file name will change. But you can send the following to them To implement sending messages with Ctrl+Enter on the webui page For openclaw v2026.3.24, in this file ``` /usr/lib/node_modules/openclaw/dist/control-ui/assets/index-Ij2djnNX.js ``` Find the key code ``` if(n.key===`Enter`&&!n.shiftKey){   if(n.isComposing||n.keyCode===229||!e.connected)return;   n.preventDefault(),t&&(e.d...

Openclaw webui 修改为 Ctrl Enter 发送信息

基于 openclaw v2026.3.24 为了实现在webui的页面上, 实现 ctrl enter 发送信息 在这个文件 ``` /usr/lib/node_modules/openclaw/dist/control-ui/assets/index-Ij2djnNX.js ``` 找到关键代码 ``` if(n.key===`Enter`&&!n.shiftKey){   if(n.isComposing||n.keyCode===229||!e.connected)return;   n.preventDefault(),t&&(e.draft.trim()&&f.push(e.draft),e.onSend()) } ``` 把  ``` if(n.key===`Enter`&&!n.shiftKey){ ``` 修改为 ``` if(n.key===`Enter`&&n.ctrlKey&&!n.shiftKey){ ```

Multi-Agent Collaboration in OpenClaw WebUI Setup Guide

Preface openclaw official version has been upgraded. I want to replicate the experiment of the previous multi-agent collaboration approach on the new version. However, I found that session_send just wouldn't succeed no matter what. Later, one time a message went through successfully, and I asked IT how it works under the hood. IT said it uses the following method openclaw agent --agent ... --message ... --json source I went to check the documentation, and it does work. So I changed the multi-agent collaboration approach to use this method to send messages And this time I'm going to use webui, which is more suitable for viewing sessions than tui Practice openclaw webui connection - omitted. I used the simplest method: set up an ssh tunnel in the local cmd command line, then access the url with token in the local browser * If you are already running openclaw on a local computer, then of course it's even simpler. In agent main, use the following natural language instructions ...

Openclaw webui 使用多 Agent 协同完成任务 Openclaw

前言 openclaw 官方版本升级了. 我想在新版本上重复实验一下 之前的多agent协作 方案. 但是, 发现session_send怎么都不成功. 后来有一次发信息成功了, 我问TA底层是怎么实现的, TA说是用的下面这个方法 openclaw agent --agent ... --message ... --json source 我跑过去一看文档, 可以啊. 于是把多Agent协作方案改为使用这种方式发送信息 而且这次我准备用webui, 比tui更适合看session

Building an OpenClaw Agent Team with TUI Collaboration

Preface In the previous post, we configured multiple Agents in TUI to achieve context isolation Now let's try having different agents play different roles and work together. Build an Agent Team I've done a lot of experimentation. Based on my experience, it's best to first have openclaw study its own documentation and summarize it in context. Study the documentation of openclaw yourself, especially agent setup and communication between agents Send the following requirements in natural language in the TUI (the blue parts are up to you) Create a new agent collaboration team, with multiple agents in the team Create these agents, set their identities, and the collaboration relationships between them Note: add new ones, keep the existing agent main Note: these are agents, not subagents In order for agents to send messages to each other, pay attention to modifying the openclaw.json file parameters tools.sessions.visibility = all tools.agentToAgent.enabled = true Agent No. 1 Name ...

Openclaw 命令行 TUI 中 使用多 Agent 协同完成任务

前言 上一篇我们在TUI配置了多Agent实现上下文隔离 现在我们试试让不同的agent扮演不同的身份, 协同工作.

Install CPA Proxy on Oracle VPS Ubuntu Guide

Now CPA installation tutorials are everywhere. Here I want to record my own operation process. Oracle VPS, Ubuntu system, using a non-root user, without sudo -i  Official installation script curl -fsSL https://raw.githubusercontent.com/brokechubb/cliproxyapi-installer/refs/heads/master/cliproxyapi-installer | bash source Pay attention to the information output by the script Execute command #1, enter your installation directory cd /home/ubuntu/cliproxyapi * If you are a root user, this directory will be different from mine, use your own directory as the reference Execute command #2, check whether the cpa background process can run, and whether there are any errors ./cli-proxy-api Open a new SSH session, test with curl curl localhost:8317 * Note: 8317 is the default port for cpa You should get a result like this {"endpoints":["POST /v1/chat/completions","POST /v1/completions","GET /v1/models"],"message":"CLI Proxy API Server"} A...

自建 CPA cliproxyapi 汇聚各路白嫖公益站 提供给Openclaw或Hermes 在 甲骨文Oracle ARM VPS Ubuntu系统 用非root用户 不用 sudo -i 可以用官方安装脚本

现在CPA的安装教程遍地都是了. 这里我想记录一下自己的操作过程 甲骨文Oracle VPS Ubuntu系统 用非root用户 不用 sudo -i 

Bind Openclaw Multi-Agent to Telegram Group Topics

Preface In the previous post we applied multi-Agent in Openclaw TUI What if we want to conveniently use Openclaw multi-Agent via Telegram? Deploy Openclaw Complete the installation of Openclaw Complete the openclaw onboard deployment During the deployment process, set the model, and set the telegram bot token The above process is omitted. Set up a Telegram group Create a new Telegram group,  Turn on the topic feature. Invite your Telegram bot into the group, Set your Telegram bot as the group admin. The above process is omitted. Use different topics in the Telegram group to bind different Openclaw Agents Search for the bot @getidsbot (userid 186675376) Send /start to learn your own account's userid 391932510 Invite the bot @getidsbot (userid 186675376) into your group to learn the group's id -1003856644307 In the openclaw tui, send the following instruction using natural language (The blue parts are up to you) Please establish binding relationships between different topics in ...

在Telegram group电报群组中使用不同的topic话题binding绑定不同的Openclaw Agent智能体

前言 上一篇我们在Openclaw TUI中应用了多Agent 如果我们想用 Telegram 方便地使用 Openclaw 多Agent 呢?

Using Openclaw Multi-Agent in TUI for Parallel Tasks

Preface When using Openclaw, you may encounter the following situation. You are currently working on a complex task and have not finished it yet. Suddenly, a temporary question comes to mind. For example, you are discussing with Openclaw how to set up the multi-Agent feature in a Telegram group, and you're halfway through, still encountering issues, and haven't finished. (1) You temporarily see someone discussing whether Openclaw can "see" bash one-click commands on a web page, and whether it is blocked by security settings. You want to give it a try. (2) If you insert the discussion of (2) in the middle of the discussion of (1), then, On one hand, the context of (1) will be brought into the processing of (2), introducing unnecessary information interference and token usage. On the other hand, when (2) is done and you continue discussing (1), the context of (2) will be brought into (1). If (2) is a particularly simple question that does not require interaction, you ca...