OpenClaw skill — 召唤DeepSeek辅助AI参与Telegram群讨论
# Call Agents Help > **Let your AI summon minions!** / **让你的 AI 召唤小弟!** An open-source OpenClaw skill that lets your AI summon other AI bots into group chats for multi-agent discussions. 一个开源的 OpenClaw 技能,让你的 AI 在群聊中召唤其他 AI 机器人进行多智能体讨论。 --- ## What is this? / 这是什么? This is an OpenClaw skill that enables multi-agent discussions in Telegram groups. Your main AI (OpenClaw) can call other AI models (DeepSeek, DeepSeek, etc.) to join the conversation — each with its own persona, speaking through its own Telegram bot. 这是一个 OpenClaw 技能,可以在 Telegram 群里实现多 AI 讨论。你的主 AI(OpenClaw)可以召唤其他 AI 模型(DeepSeek、DeepSeek 等)加入对话——每个都有自己的人设,通过各自的 Telegram bot 发言。 **No need for multiple OpenClaw instances. No Docker. No complex setup.** **不需要部署多个 OpenClaw,不需要 Docker,不需要复杂的环境配置。** ## Why? / 为什么做这个? Normally, if you want two AIs to discuss a problem, you have to copy-paste messages between them like a human messenger. That's tedious, slow, and you lose context along the way. 通常情况下,如果你想让两个 AI 讨论一个问题,你得像信使一样在它们之间来回复制粘贴消息。这很累、很慢,而且上下文会丢失。 With this skill: 用了这个技能之后: - Multiple AI bots discuss directly in a group chat / 多个 AI 机器人直接在群聊里讨论 - They challenge each other, catch errors, and converge on answers / 它们会互相质疑、纠错,最终收敛到一致的答案 - The entire conversation is visible to you in real time / 整个对话过程对你完全可视化 - You can interrupt, redirect, or ask follow-up questions anytime / 你可以随时打断、改变方向或追问 - Add as many bots as you want / 可以添加任意数量的 bot ## How it works / 工作原理 ``` You (in Telegram group) │ ▼ OpenClaw (main AI, e.g. 小龙虾) │ reads SKILL.md → runs deepseek_speak.py │ loads subsoul.md (persona identity) │ calls DeepSeek API │ sends response via helper bot ▼ Helper Bot (e.g. 批判派🔍) speaks in the same group │ ▼ OpenClaw reads the response, replies, calls helper again... │ ▼ Multi-round discussion until consensus or user stops it ``` The key insight: OpenClaw orchestrates everything. The helper bot is just a "mouth" — it doesn't need to run independently. This avoids the Teleg
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型