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

It eliminates the technical complexity of building a WhatsApp customer service bot. Instead of dealing with webhooks, API tokens, and server deployment, you simply answer questions about your business, and the system automatically generates, tests, and deploys a fully functional AI agent.

How it works

It uses Claude Code to guide you through a setup process. First, it interviews you about your business (e.g., hours, menu, tone). Then, it writes the necessary Python code, sets up a local database for memory, and configures connections to WhatsApp via Zernio or Meta Cloud API. You can test the agent locally in your terminal, and once satisfied, deploy it to a service like Railway to handle live customer messages.

Who it’s for

Business owners and builders who want a custom AI-powered WhatsApp assistant but do not want to write or maintain complex code. It is designed for anyone needing to automate FAQs, bookings, or lead qualification.

Highlights

  • No coding required: Claude Code handles the generation and updates based on your natural language requests.
  • Privacy-focused: All data, including your database and API keys, runs on your own infrastructure.
  • Built-in memory: The agent remembers previous conversations with each customer.
  • Reliable architecture: Uses a "respond first, process later" design to ensure messages are handled efficiently without duplication.
  • Flexible integration: Supports both Zernio (recommended for easy setup) and Meta Cloud API.

Related

  • Project
    chrisblattman/claudeblattman

    Open‑source, no‑code guide for building Claude‑based desktop AI agents; includes docs, a Claude plugin starter‑kit, optional Python skill installer, and templates for custom agents.

  • Project
    TechNomadCode/AI-Product-Development-Toolkit

    A toolkit of guided AI prompts, a step-by-step app builder (Next.js/Supabase/Vercel), installable skills for Claude Code/Codex, and Claude Code agent configs — designed to make planning, building, and launching AI-assisted products structured and less messy. Its core trick: AI interviews you first instead of guessing, and keeps everything in one organized flow.

  • Project
    ajsahni/agents-office

    Agents Office is a beta, locally‑run visual platform that turns Claude into a team of 35 role‑based AI agents. You type tasks, the system routes them to the right agent (or a team), the agents use Claude Code connectors (Gmail, Slack, Chrome, etc.) to do the work, and results are saved as notes in your personal “Brain”. Features include customizable briefs/skills, recurring routines, a calendar view, team‑splitting, model/effort selection, and a non‑commercial license.

  • 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
    rsmdt/the-startup

    The Agentic Startup is a multi-agent AI framework for Claude Code that enforces spec-driven development: you create detailed requirements and plans, then a team of specialized agents builds, tests, reviews, and documents your code with quality gates and parallel execution. It solves the problems of unclear requirements, context limits, and inconsistent code quality.