Build a 24‑Hour Digital Assistant on MacBook with OpenClaw, MiniMax and Feishu – Access 30,000 Skills
This article walks through installing the open‑source OpenClaw AI assistant on a MacBook (or cloud server), configuring it with the MiniMax model and Feishu, enabling 24‑hour remote control, local memory, data sovereignty, and thousands of ready‑made skills, while highlighting setup commands, security considerations, and cost factors.
Overview
OpenClaw is an open‑source, locally‑first personal AI assistant framework that acts as an AI gateway bridging instant‑messaging (IM) platforms and large language models. It runs continuously on a user’s machine, enabling remote control, long‑term memory, and data sovereignty.
Core capabilities
Remote control : IM messages (e.g., Feishu, DingTalk, Enterprise WeChat) can trigger browser actions, file operations, and return results.
Long‑term memory : Stores local files and conversation history for context‑aware responses.
Data sovereignty : API keys and private documents remain on the local host; no third‑party cloud execution.
Installation
Run the one‑click installer:
curl -fsSL https://openclaw.bot/install.sh | bashFor Windows PowerShell: iwr -useb https://openclaw.ai/install.ps1 | iex Install Node.js (v22 or later) and nvm, then install the CLI globally: npm install -g openclaw@latest Start the interactive onboarding: openclaw onboard During onboarding select a large‑model provider (MiniMax is recommended). Create an API key on the MiniMax portal, then place it in ~/.openclaw/openclaw.json. For users in China replace the model base URL with https://api.minimaxi.com/anthropic and enable the Auth Header flag.
Feishu integration
Create a Feishu app at https://open.feishu.cn/app, record the App ID and App Secret.
In the Feishu console add a robot; in OpenClaw UI select “Channels” and fill the Feishu credentials.
Configure event callbacks as “long‑link mode”, add permission im:message (and optionally contact:user.base:readonly).
Restart the gateway: openclaw gateway restart Verify with: openclaw status or open the dashboard at http://127.0.0.1:18789.
Skill management
The repository https://github.com/openclaw/openclaw/tree/main/skills contains over 35 000 ready‑made skills. To add a skill use the skills CLI:
npx skills add https://github.com/vercel-labs/skills --skill find-skillsAfter registration the skill appears in the backend and can be invoked through the assistant.
Operational commands
openclaw doctor– health‑check of the gateway. openclaw status – shows running processes. openclaw dashboard – opens the web UI (default http://127.0.0.1:18789).
Logs, memory files, and scheduled‑task definitions are stored under ~/.openclaw/.
Security and practical considerations
Deep system access means misconfiguration can lead to prompt‑injection attacks or exposure of the control interface.
Deployment requires familiarity with Node.js, nvm, and IM platform configuration; it is oriented toward developers.
Using large‑model APIs (OpenAI, Anthropic, MiniMax) incurs usage costs proportional to request volume.
References
GitHub repository: https://github.com/openclaw/openclaw
MiniMax integration guide: https://platform.minimaxi.com/docs/solutions/moltbot
Skills catalog: https://skills.sh/ (≈35 000 skills)
Signed-in readers can open the original source through BestHub's protected redirect.
This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactand we will review it promptly.
Ubiquitous Tech
A ubiquitous public account for pirate enthusiasts, regularly sharing curated experiences, tech learning, and growth insights. Currently publishing articles on AI RAG customer service, AI MCP technology, and open-source design. Personal free Knowledge Planet: Awakening New World Programmer.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.
