SkillAgentSearch skills...

wacrew

Open-source WhatsApp AI automation: inbox sorted by wait time, replies in your own voice with human-paced delivery, client CRM, live 2D office and an MCP server for Claude Code and Codex.

Install / Use

claude mcp add sumioshi -- npx -y github:sumioshi/wacrew

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

84/100

Category

Automation

Supported Platforms

Claude Code
Claude Desktop
OpenAI Codex

Our assessment of wacrew

wacrew scores 84/100 on our quality scale, 1988th of 2,758 Automation skills we index.

Its MCP Server is 16 KB long, well organised into 11 sections with 9 code examples: a thorough specification that gives an agent plenty to work with.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
4/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 3 days ago, so wacrew is actively maintained.
  • It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 97/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

wacrew compared with similar skills

All 4 of these similar skills score higher than wacrew; compare them before choosing.

SkillScoreStarsUpdatedFormat
wacrew (this skill)by sumioshi84103d agoMCP Server
Agent-Reachby Panniantong100114.0ktodayCLAUDE.md
hyperframesby heygen-com10088.2ktodayCLAUDE.md
rufloby ruvnet10082.3ktodayCLAUDE.md
headroomby headroomlabs-ai10080.5ktodayCLAUDE.md

Frequently asked questions

How do I install wacrew?
Run claude mcp add sumioshi -- npx -y github:sumioshi/wacrew. The install tabs above show the steps for each supported agent.
Which AI agents does wacrew work with?
It is written for Claude Code, Claude Desktop and OpenAI Codex, as a MCP Server file. Other agents that read the same format can often use it too.
Is wacrew safe to use?
It is Apache-2.0-licensed and scores 97/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is wacrew still maintained?
The repository was last updated 3 days ago, so wacrew is actively maintained.
<p align="center"><img src="docs/assets/wacrew-mark.svg" alt="WACrew" width="96"></p> <h1 align="center">WACrew</h1> <p align="center"> <b>An AI that answers your WhatsApp in your own voice, so clients talk to you, not to a bot.</b><br> It sorts every group and chat by who has waited longest, writes with your punctuation and rhythm,<br> and delivers at a human pace. You approve each reply or leave a chat on auto.<br> Open source, self-hosted, with an MCP server so Claude Code, Cursor or Codex can work the chats too. </p> <p align="center"> <a href="https://railway.com/deploy/wacrew?referralCode=8ZIi5q&utm_medium=integration&utm_source=template&utm_campaign=readme"><img alt="Deploy on Railway" src="https://railway.com/button.svg" height="32"></a> <a href="https://www.hostinger.com/vps-hosting?REFERRALCODE=ORISHODIRBUH"><img alt="Deploy on Hostinger" src="docs/assets/deploy-hostinger-en.svg" height="32"></a> <br><sub>One click on Railway, a VPS with 20% off on Hostinger (referral links that help fund the project), or <a href="#quick-start">run it on your machine</a>.</sub> </p> <p align="center"> <a href="./LICENSE"><img alt="License: Apache 2.0" src="https://img.shields.io/badge/license-Apache_2.0-blue.svg" height="20"></a> <a href="https://nodejs.org"><img alt="Node 20+" src="https://img.shields.io/badge/node-%E2%89%A520-43853d.svg" height="20"></a> <a href="https://github.com/WhiskeySockets/Baileys"><img alt="Built with Baileys" src="https://img.shields.io/badge/built%20with-Baileys-25D366.svg" height="20"></a> <a href="https://github.com/sponsors/sumioshi"><img alt="Sponsor" src="https://img.shields.io/github/sponsors/sumioshi?label=Sponsor&logo=githubsponsors&color=ea4aaa" height="20"></a> <a href="https://modelcontextprotocol.io"><img alt="MCP server" src="https://img.shields.io/badge/MCP-37%20tools-6366f1.svg" height="20"></a> <a href="https://www.npmjs.com/package/wacrew-mcp"><img alt="npm" src="https://img.shields.io/npm/v/wacrew-mcp.svg?label=npm" height="20"></a> <a href="https://glama.ai/mcp/servers/sumioshi/wacrew"><img alt="Glama score" src="https://glama.ai/mcp/servers/sumioshi/wacrew/badges/score.svg" height="20"></a> </p> <p align="center"> <a href="https://m8ven.ai/mcp/sumioshi-wacrew-nirsqy?s=readme"><img alt="M8ven Score" src="https://m8ven.ai/badge/mcp/sumioshi-wacrew-nirsqy" height="20"></a> </p> <p align="center"><a href="https://wacrew.com.br">wacrew.com.br</a> · <a href="./README.pt-BR.md">Leia em português</a> · ⭐ <b>If WACrew helps you, a star helps others find it.</b></p> <p align="center"><img src="docs/screenshots/demo-auto.gif" width="551" alt="The AI drafts a reply; flipping AUTO on, it types and answers on its own"></p> <p align="center"><a href="https://wacrew.com.br/en/#video"><img src="docs/assets/vsl-en.jpg" width="640" alt="Watch the 55-second video: from WhatsApp chaos to every client answered"></a><br><sub>▶ Watch the 55-second video</sub></p>

Why

If you sell or deliver work over WhatsApp, you know the scene: forty client groups, a four-minute voice note in the middle of a thread, the bug screenshot lost in the scroll, and the client who wrote three days ago that nobody saw.

A chatbot does not fix that. Canned answers read like a robot, clients notice, and the relationship cools down. WACrew works differently:

  • Nobody waits. Every group and chat goes into one queue, oldest wait first, with voice notes already transcribed.
  • It sounds like you. Replies follow your punctuation, openings and rhythm, measured on your own messages, and pass a review that blocks robotic tells before they leave.
  • It moves like a person. Read receipt, typing, pauses between bubbles, and it stops if the client writes again or you answer from your phone.
  • You stay in charge. Confirm mode is the default: nothing goes out without your OK. If a client asks whether it is AI, it does not lie; it stops and hands the chat back to you.

A client conversation in WACrew: AI replies delivered in bubbles, with the client's contract, people and notes on the side

The engine that makes it read like a person:

| 2 | 25+ | 60 | ~30 s | |:---:|:---:|:---:|:---:| | writing skills: your voice and client conduct | code rules that block robot tells | history messages read before replying | median until typing starts in a live chat |

What it does

Nobody waits. Every group and direct chat lands in one queue sorted by waiting time. A client's group and their private chats show up together, back-to-back messages collapse into one block, and voice notes arrive transcribed.

Writes like you, delivers like a person. The AI reads the history and writes with your punctuation, openings and rhythm, measured on your own past messages. Before anything leaves, a deterministic review blocks robot clichés, repeated apologies and duplicate bubbles (the generic part of it is also a standalone library, botsmell). Delivery comes with read receipt, typing indicator and pauses, and it stops on its own if the client writes again or you answer from your phone.

You stay in control. In Confirm mode (the default) nothing is sent without your OK. Autonomous mode is turned on per chat. Every message records who wrote it: you on the phone, you on the panel, a teammate, or the AI.

| | | |---|---| | Today view: who is waiting, AI activity, signals and today's calendar Today. Who is waiting and for how long, what the AI is doing, signals and today's agenda. | 2D pixel-art office with one desk per client project 2D office. One desk per project. When a client writes, the desk turns red right away, with sound. | | Dashboard with message volume, first-reply time and who replied Dashboard. Volume, first-reply time, who answered, busiest clients and deliveries per month. | Clients kanban board with waiting time, tags and last message Clients. Table and board views with contract, deliveries and waiting time per client. | | Client drawer with the coding agent running in the project's repository Agent bridge (optional). If you use Orca, the client drawer shows the coding agent working on that project's repo and lets you send it commands. | Weekly Google Calendar view inside the panel Calendar. Your Google Calendar inside the panel, editable by you or by the AI. |

More screens in docs/screenshots/: org chart, team access, notifications, project links, settings and the command palette.

How it works

                          ┌────────────────────────────┐
  WhatsApp ─► collector ─►│  data/<chat>/              │◄─► web panel (Next.js, :3000)
  (Baileys)   (daemon)    │  messages.jsonl + media    │
                          │  transcripts, notes, state │◄─► MCP server (your coding agent)
                          └─────────────┬──────────────┘
                     transcriber (MLX on Apple Silicon, or an API)
  • Collector (src/): a Baileys daemon (WhatsApp Web multi-device, no browser). Baileys is isolated behind ports and adapters in src/whatsapp/. It writes every message, reaction and media file to data/<chat>/ and runs the delivery queue that sends replies at a human pace.
  • Panel (web/): Next.js 16 + React 19. Inbox, conversation view, clients, dashboard, calendar, team, 2D office, settings. Live updates over SSE.
  • MCP server (web/mcp/server.ts): 37 tools over the same data, for Claude Code, Codex, Antigravity, Gemini CLI, Qwen Code or any MCP client.
  • Transcriber (transcriber/): Whisper large-v3 via MLX, loaded on demand and released when idle. Off a Mac, set TRANSCRIBE_BACKEND=openrouter.
  • Local or cloud. Run everything on your machine, or deploy the collector and panel 24/7 with the included Dockerfile (a railway.json is provided). The local MCP can read straight from the cloud panel (WAC_MCP_REMOTE=1), downloading media on demand.

Quick start

Requirements: Node.js 20+, ffmpeg, and a WhatsApp account to pair. Local transcription needs Apple Silicon (uv tool install mlx-whisper).

git clone https://github.com/sumioshi/wacrew && cd wacrew
npm install && npm --prefix web install
cp .mcp.json.example .mcp.json
npm run dev          # collector + panel + transcriber + notifier

Open http://localhost:3000/config, scan the QR code (WhatsApp › Linked devices › Link a device), pick the groups to follow and mark who is on your team. The session is saved in auth/ and reconnects on its own.

Run it 24/7 on a VPS. WACrew only records what arrives while it is running: if your computer is off, messages from that period never reach the history or the queue. The repo ships a docker-compose.yml with a persistent volume for the WhatsApp session and data:

cp .env.example .env   # set PANEL_USER and PANEL_PASS
docker compose up -d

<a href="https://www.hostinger.com/vps-hosting?REFERRALCODE=ORISHODIRBUH"><img alt="Deploy on Hostinger" src="docs/assets/deploy-hostinger-en.svg" height="32"></a> <a href="https://railway.com/deploy/wacrew?referralCode=8ZIi5q&utm_medium=integration&utm_source=template&utm_campaign=generic"><img alt="Deploy on Railway" src="https://railway.com/button.svg" height="32"></a>

<sub>Referral links: you get a discount or credits, and the project earns a commission that helps keep it maintained. On Railway the template sets up the volume, the login and a generated password for you.</sub>

Other clouds. Run the prebuilt image ghcr.io/sumioshi/wacrew or build the Dockerfile on any host with a volume at /data. Set PANEL_USER and PANEL_PASS to protect the panel with login; without them the panel is open, which is only fine on localhost.

MCP tools

The server is registered by .mcp.json (project scope). Claude Code and Qwen Code read it and ask for approval on first use.

From npm, without cloning. With the panel running on a VPS, add the MCP to any client with wacrew-mcp:

claude mcp add wacrew -e WAC_CLOUD_URL=https://your-panel.example.com \
  -e WAC_CLOUD_USER=admin -e WAC_CLOUD_PASS=change-me -- npx -y wacrew-mcp

Antigravity plugin. The repo is also an Antigravity plugin, with the MCP and the skills (plantao, autonomo, link-whatsapp, comunicacao-cliente):

agy plugin install https://github.com/sumioshi/wacrew

It installs turned off. Open /plugin (or Customizations in the editor), turn on WACrew and fill in the panel URL, login and password; other accounts go in the URL field after a space, as below. To add only the MCP, flags go before the name:

agy mcp add -e WAC_CLOUD_URL=https://your-panel.example.com \
  -e WAC_CLOUD_USER=admin -e WAC_CLOUD_PASS=change-me wacrew npx -y wacrew-mcp

More than one WhatsApp. One server can talk to several panels. Add the others in WAC_CONTAS as name=https://login:password@address, separated by spaces (or put them after the main address in WAC_CLOUD_URL). Every tool then takes an optional conta parameter, and the agent picks the account per call. WAC_CONTA_NOME names the default one:

claude mcp add wacrew -e WAC_CLOUD_URL=https://work.example.com \
  -e WAC_CLOUD_USER=admin -e WAC_CLOUD_PASS=change-me -e WAC_CONTA_NOME=work \
  -e WAC_CONTAS="personal=https://admin:other-pass@personal.example.com" -- npx -y wacrew-mcp

| Area | Tools | |---|---| | Read | listar_grupos, ler_mensagens, buscar, listar_contatos, caixa_de_entrada, novidades, resumo_do_dia, ler_notas, estado_triagem | | Media | transcrever, ver_imagem, ver_video, assistir_video, ler_documento | | Reply | preparar_resposta,

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars10
CategoryAutomation
Updated3d ago
Forks5

Languages

TypeScript

Trust signals

97/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 info