CSA: Open-source customer support agents powered by Gemini Stream API. Watch as our agent network handles support through voice and screen sharing, working together 24/7 to solve customer issues.
# CSA (Customer Service Agent)
[](https://youtu.be/u60zuj1tqBI)
An open-source customer service platform powered by Google's Gemini Stream API. Watch as our AI agent network handles support through voice and screen sharing, working together 24/7 to solve customer issues.
## Overview
CSA provides a modern, AI-powered customer service solution that enables:
- Real-time voice interactions with AI agents
- Screen sharing capabilities
- 24/7 customer support availability
- Customizable AI agent personalities and instructions
- Dark/light theme support
## Tech Stack
- **Frontend**: Next.js 15, React, TypeScript
- **Backend**: MongoDB
- **AI**: Google Gemini Stream API
- **Styling**: Tailwind CSS, shadcn/ui
- **State Management**: Redux, Zustand
- **API Communication**: React Query, Axios
- **Form Handling**: React Hook Form, Zod
## Prerequisites
- Node.js 18+
- MongoDB database
- Google Cloud Project with Gemini API access
- Environment variables setup
## Getting Started
1. Clone the repository:
```bash
git clone https://github.com/your-username/csa.git
cd csa
```
2. Install dependencies:
```bash
npm install
```
3. Create a `.env` file in the root directory:
```bash
cp .env.example .env
```
4. Start the development server:
```bash
npm run dev
```
5. Open [http://localhost:3000](http://localhost:3000) in your browser
## Features
### Current Features
- Create and manage AI customer service agents
- Real-time voice communication with AI agents
- Screen sharing during support sessions
- Dark/light theme support
- Customizable agent instructions and personalities
- Session history tracking
### Upcoming Features
- RAG + Tool Usage
- Agent Performance Metrics
- Agent Chat History
- Agent Embeddings
- Integration with Slack & Email
- Agent collaboration capabilities
- Custom voice options for agents
- Chat transcript export
## Contributing
We welGoogle'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.
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.
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.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
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.