Back to Agents
WhatsApp-agent
iamEtornam March 24, 2026
10 copies 0 downloads
WhatsApp bot powered by Google Gemini 3 Flash Preview and the Koog AI agent framework.
Agent Definition
<div align="center">
<img src="assets/banner.png" alt="WhatsApp AI Bot Banner" width="800">
# WhatsApp AI Bot
[](https://kotlinlang.org/)
[](https://ktor.io/)
[](https://aistudio.google.com/)
[](LICENSE)
**A production-ready WhatsApp bot powered by Google Gemini 3 Flash Preview and the Koog AI agent framework.**
Built with Kotlin and Ktor, it handles real conversations, sends rich media, reacts to messages, and presents interactive button menus — all through the Kapso WhatsApp Cloud API.
</div>
---
## 🚀 Features
- **🧠 Intelligent Reasoning** — Powered by Gemini 3 Flash Preview for context-aware responses and tool execution.
- **📱 Rich Media Support** — Understands and sends text, images, videos, audio clips, documents, locations, reactions, and stickers.
- **💾 Per-User Memory** — Maintains conversation history independently for each user (up to 20 messages).
- **🛡️ Secure Webhooks** — HMAC-SHA256 signature verification and automatic message deduplication.
- **⚡ High Performance** — Built on Ktor and Coroutines with optimized thread management.
- **🌍 Multilingual** — Automatically responds in the same language the user writes in.
---
## 🛠️ What It Does
When a WhatsApp user sends a message to your number, the bot:
1. **Receives** it via a secure webhook (HMAC-SHA256 verified).
2. **Analyzes** it with a per-user AI agent that has full conversation memory.
3. **Reasons** with Gemini 3 Flash Preview and selects the appropriate response action.
4. **Responds** with a text reply, image, document, emoji reaction, or interactive button menu.
---
## 🏗️ Architecture
```mermaid
graph TD
User([WhatsApp User]) --> Kapso[Kapso API]
KapsoComments
More Agents
View allresearch
NotebookLM
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
G
Googlebrowser
Project Mariner (Browser Agent)
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
G
Google DeepMindmultimodal
Project Astra (Multimodal Agent)
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
G
Google DeepMindenterprise
Gemini Enterprise Agent Platform
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
G
Google Cloudresearch
Gemini Deep Research Agent
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
G
Googlecanvas
Gemini Canvas Agent
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.
G
Google