by cyhhao
Your AI agent army, commanded from Slack/Discord/Telegram/Wechat/Lark. Stream Claude Code, OpenCode, or Codex in real-time — from anywhere.
# Add to your Claude Code skills
git clone https://github.com/cyhhao/vibe-remoteNo comments yet. Be the first to share your thoughts!
Supported Agents
You're at the beach. Phone buzzes — production's on fire.
Old you: Panic. Find WiFi. Open laptop. Wait for IDE. Lose your tan.
Vibe Remote you: Open Slack, Discord, Telegram, or WeChat. Type "Fix the auth bug in login.py". Watch Claude Code fix it in real-time. Approve. Sip margarita.
AI works. You live.
curl -fsSL https://raw.githubusercontent.com/cyhhao/vibe-remote/master/install.sh | bash && vibe
That's it. Browser opens -> Follow the wizard -> Done.
We recommend the WSL setup on Windows because it has the best compatibility.
If you are new to WSL, this guide explains:
| Problem | Solution | |---------|----------| | Claude Code is amazing but needs a terminal | Slack/Discord/Telegram/WeChat/Lark IS your terminal now | | Context-switching kills flow | Stay in one app | | Start on desktop, continue on phone | Resume the exact agent session from the current project in seconds | | Can't code from phone | Yes you can | | Multiple agents, multiple setups | One chat app, any agent |
Supported Agents:
| | Vibe Remote | OpenClaw | |---|---|---| | Setup | One command + web wizard. Done in 2 minutes. | Gateway + channels + JSON config. Expect an afternoon. | | Security | Local-first. Socket Mode / WebSocket only. No public endpoints, no inbound ports, minimal attack surface. | Gateway exposes ports. More moving parts, more attack surface. | | Token cost | Thin transport layer — relays messages between your IM and agent. Zero LLM overhead from the middleware itself. | Every message carries a long system context for maintaining agent persona, IM tooling, and orchestration plumbing. Tokens burn on overhead before your actual task even starts. |
OpenClaw is a personal AI assistant — great for casual chat, but its always-on agent loop makes it expensive for real productivity workloads. Vibe Remote is not an agent framework. It's a remote control — a minimal bridge between your chat app and whatever AI agent you already use. It adds no extra intelligence layer, no extra token spend, and no extra attack surface. Every token goes straight to your task.
One-command install, guided configuration. No manual token juggling.
Real-time status, health monitoring, and quick controls.
Per-channel agent configuration. Different projects, different agents.
Get notified the moment your AI finishes. Like assigning tasks to employees — delegate, go do something else, and come back when the work is done. No need to babysit.
Each Slack/Discord/Telegram/WeChat/Lark chat scope is an isolated workspace. Open 5 chats, run 5 parallel tasks. Context stays separate.
Laptop closed. Commute started. Production still needs you.
Vibe Remote lets you reopen real agent sessions from your current working directory across Claude Code, OpenCode, and Codex. Pick the latest session, jump from desktop to mobile, and keep going without re-explaining the task, hunting for an old thread, or losing the thread of thought.
When your agent needs input — file selection, confirmation, options — your chat app pops up buttons or a modal. Full CLI interactivity, zero terminal required.
Ask your agent to schedule work for later, repeat a prompt on a cron, or queue a one-shot async follow-up after a long-running job.
vibe taskvibe hook send┌──────────────┐ ┌──────────────┐ ┌──────────────┐
│ You │ Slack │ │ stdio │ Claude Code │
│ (anywhere) │ Discord │ Vibe Remote │ ──────────▶ │ OpenCode │
│ │ Telegram │ (your Mac) │ ◀────────── │ Codex │
│ │ WeChat │ │ │ │
│ │ Lark │ │ │ │
└──────────────┘ └──────────────┘ └──────────────┘