Hainrixz/whatsapp-agentkit

Construye tu agente de WhatsApp con IA en menos de 30 minutos. Claude Code te entrevista y escribe todo el código. Zernio o Meta Cloud API. Sin saber programar.

What it solves

WhatsApp AgentKit simplifies the creation and deployment of AI-powered WhatsApp customer service agents. It removes the "plumbing" work—handling webhooks, signatures, tokens, and deployment—allowing business owners to create a functional agent by simply answering questions about their business rather than writing code.

How it works

The project uses Claude Code to automate the entire development lifecycle. After running a setup script, the user interacts with Claude Code via a /build-agent command, which executes five phases:

  1. Environment Setup: Verifies Python and installs dependencies.
  2. Interview: Claude asks the user about their business name, purpose, tone, hours, and pricing/menus.
  3. Construction: Claude generates a full project structure including a FastAPI server, a "brain" connected to Claude API, memory for client history, and provider adapters.
  4. Testing: The user tests the agent via a local terminal chat simulator.
  5. Deployment: Guides the user through hosting on GitHub and Railway.

It supports two WhatsApp connection methods: Zernio (a simplified wrapper) and the Meta Cloud API (direct official access). To prevent duplicate messages and timeouts, it implements an immediate webhook response pattern and event deduplication.

Who it’s for

Business owners and builders (specifically targeting the LATAM market) who want an AI agent to handle FAQs, appointments, or lead qualification on WhatsApp without needing deep programming knowledge.

Highlights

  • No-Code Setup: The agent is built through a natural language interview with Claude Code.
  • Provider Flexibility: Easily switch between Zernio and Meta Cloud API using a pattern adapter.
  • Reliable Messaging: Prevents duplicate responses via event ID deduplication and asynchronous processing.
  • Secure Webhooks: Implements HMAC-SHA256 signature verification to prevent unauthorized message injection.
  • Memory Persistence: Maintains individual conversation histories for every customer.

Related

  • Project
    shareAI-lab/learn-claude-code

    A 17‑lesson tutorial that teaches you how to build the surrounding “harness” code for an LLM‑based coding agent (Claude). It walks through adding tools, permissions, context management, memory, task scheduling, multi‑agent coordination, and goal‑driven termination, all around a simple agent‑loop that lets the model decide when to call tools.

  • Project
    Hainrixz/the-architect

    A Claude Code meta-agent that designs rigorous software blueprints with verified stacks and strict acceptance criteria to guide autonomous AI builders.

  • Project
    rsmdt/the-startup

    A multi-agent AI framework for Claude Code that implements a spec-driven development workflow to turn ideas into shipped code via structured planning and parallel specialist agents.

  • Dispatch
    ServiceNow Integrates Claude as Default Model for Build Agent and AI Platform

    ServiceNow has adopted Claude as the default model for its Build Agent and a preferred model for its AI Platform to automate enterprise workflows and increase internal productivity.

  • Project
    composio-community/secure-openclaw

    A personal 24/7 AI assistant that integrates Claude or Opencode with messaging platforms like WhatsApp and Telegram to provide tool access and persistent memory.