wacrew

mcp
Security Audit
Warn
Health Warn
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Warn
  • process.env — Environment variable access in .agents/skills/run-whatsapp-automation/driver.mjs
  • process.env — Environment variable access in .claude/skills/run-whatsapp-automation/driver.mjs
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

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.

README.md

WACrew

WACrew

An AI that answers your WhatsApp in your own voice, so clients talk to you, not to a bot.
It sorts every group and chat by who has waited longest, writes with your punctuation and rhythm,
and delivers at a human pace. You approve each reply or leave a chat on auto.
Open source, self-hosted, with an MCP server so Claude Code, Cursor or Codex can work the chats too.

Deploy on Railway Deploy on Hostinger
One click on Railway, a VPS with 20% off on Hostinger (referral links that help fund the project), or run it on your machine.

License: Apache 2.0 Node 20+ Built with Baileys Sponsor MCP server npm Glama score

M8ven Score

wacrew.com.br · Leia em português · ⭐ If WACrew helps you, a star helps others find it.

The AI drafts a reply; flipping AUTO on, it types and answers on its own

Watch the 55-second video: from WhatsApp chaos to every client answered
▶ Watch the 55-second video

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): 36 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

Deploy on Hostinger Deploy on Railway

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.

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

In Antigravity, the agy CLI takes the same command, with the flags 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
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, revisar_texto, responder, responder_midia, editar_mensagem, reagir, status_envio, cancelar_envio
Triage and CRM marcar_resolvido, silenciar_grupo, anotar, etiquetar, alertar_chat, definir_modo, definir_contrato, registrar_feature, dashboard, editar_perfil
Calendar agenda_ver, agenda_marcar, agenda_editar, agenda_apagar

Highlights:

  • buscar finds text inside transcripts too.
  • ver_imagem and ver_video hand the media to the model, which is handy for bug screenshots. assistir_video has a Gemini model watch a video with its audio, attached or from a link.
  • responder returns a ticket. The message leaves later at a human pace: seconds in a live chat, minutes to hours in a cold one. The ticket is interrupted if the client writes or you answer by hand. status_envio tracks it and cancelar_envio cancels it.
  • preparar_resposta returns your recent style and what the client left open. Pass 2 or 3 candidatos to responder and the least out-of-character one is sent.

Tool names are in Portuguese because the project started in Brazil. Descriptions are clear enough for any model.

Configuration

Everything has a default. Copy .env.example to .env and adjust what you need.

Variable What it does
PANEL_USER, PANEL_PASS Panel login. Required when the panel is reachable from the internet.
OPENROUTER_API_KEY Posture check before sending, video watching and API transcription.
COPILOT_PROVIDER, ANTHROPIC_API_KEY, COPILOT_OPENAI_API_KEY The in-panel copilot (Anthropic or any OpenAI-compatible API).
TRANSCRIBE_BACKEND mlx (local, default on a Mac) or openrouter.
WAC_MCP_REMOTE, WAC_CLOUD_URL, WAC_CLOUD_USER, WAC_CLOUD_PASS Point the local MCP and sync at your cloud panel.
WAC_NOME_OPERADOR, WAC_SKILL_VOZ Your first name and the voice skill the AI loads before writing.
GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET Calendar and Google sign-in.
CONTROL_TOKEN Bearer token for the external control API.
DATA_DIR, AUTH_DIR, LOG_LEVEL Where data and the session live, and log verbosity.

There is also a public REST API documented in docs/api-v1.md.

What gets stored

data/<chat>/
  messages.jsonl     one line per message (the AI's "database")
  reactions.jsonl    emoji reactions
  log.md             the same conversation, human-readable
  audio/ video/ image/ document/ transcripts/

data/, auth/, .env and groups.config.json are git-ignored. Never commit them.

Read this before using it

  • This is not the official WhatsApp API. WACrew links to your account as one more device, through Baileys. It is built to answer people who already talk to you. Bulk messaging and cold outreach can get your number banned.
  • No old history. Capture starts when you pair the number.
  • Sending is real. The panel and the control API send messages as you. Keep them on localhost or behind login.
  • WACrew is an independent project, not affiliated with WhatsApp or Meta.

Contributing

If WACrew saves you time, consider sponsoring the project. It pays for the hours that keep it maintained.

Issues and pull requests are welcome.

npm test            # Vitest
npx tsc --noEmit    # typecheck

Shared logic between the panel and the MCP lives in web/lib/. See CONTRIBUTING.md.

Sponsors

WACrew is free and open source. Sponsors keep it maintained and get their name or logo here.

Become the first sponsor

License

Apache 2.0 © Rodrigo Sumioshi. See NOTICE.

Reviews (0)

No results found