Loading repository data…
willnapolinighub / repository
A powerful, production-ready hierarchical multi-agent framework with a visual builder for creating, orchestrating, and deploying AI agent systems. Built with TypeScript, Next.js 16, and featuring a drag-and-drop workflow canvas.
A powerful, production-ready hierarchical multi-agent framework with a visual builder for creating, orchestrating, and deploying AI agent systems. Built with TypeScript, Next.js 16, and featuring a drag-and-drop workflow canvas.
| Provider | Models | Features |
|---|---|---|
| OpenAI | GPT-4o, GPT-4 Turbo | Full tool calling support |
| Ollama | Llama, Mistral, Qwen | Run locally, zero API costs |
| OpenRouter | Claude, Gemini, GPT | Multi-model gateway |
| n8n | Custom workflows | Integration with automation |
| AgentRouter | Auto-routing | Intelligent model selection |
| Custom | Any OpenAI-compatible | Bring your own API |
Analytics Tools:
Research Tools:
Content Tools:
# Clone the repository
git clone https://github.com/yourusername/multi-agent-system.git
cd multi-agent-system
# Install dependencies
bun install
# Set up environment variables
cp .env.example .env.local
# Start development server
bun run dev
Open http://localhost:3000 to see the application.
# Required: OpenAI API Key (for z-ai-web-dev-sdk)
OPENAI_API_KEY=your_openai_api_key
# Optional: Other provider API keys
OLLAMA_BASE_URL=http://localhost:11434
OPENROUTER_API_KEY=your_openrouter_key
N8N_WEBHOOK_URL=http://localhost:5678/webhook
CUSTOM_AI_API_KEY=your_custom_key
┌─────────────────────────────────────────────────────────────┐
│ User Interface │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────────────┐ │
│ │ Landing Page│ │ Agent App │ │ Visual Builder │ │
│ └─────────────┘ └─────────────┘ └─────────────────────┘ │
└─────────────────────────────────────────────────────────────┘
│
┌─────────────────────────────────────────────────────────────┐
│ API Layer │
│ ┌───────────────┐ ┌───────────────┐ ┌────────────────┐ │
│ │ /api/agents │ │ /api/settings │ │ /api/analytics │ │
│ └───────────────┘ └───────────────┘ └────────────────┘ │
└─────────────────────────────────────────────────────────────┘
│
┌─────────────────────────────────────────────────────────────┐
│ Agent System Core │
│ │
│ ┌─────────────────────────────────────────────────────┐ │
│ │ Master Orchestrator │ │
│ │ (Plans, Coordinates, Aggregates Results) │ │
│ └───────────┬──────────────┬──────────────┬───────────┘ │
│ │ │ │ │
│ ┌───────────▼────┐ ┌──────▼───────┐ ┌────▼────────────┐ │
│ │ Analytics │ │ Research │ │ Content │ │
│ │ Orchestrator │ │ Orchestrator │ │ Orchestrator │ │
│ └────────┬───────┘ └──────┬───────┘ └────────┬────────┘ │
│ │ │ │ │
│ ┌────────▼────┐ ┌──────▼──────┐ ┌──────▼──────┐ │
│ │ Analytics │ │ Research │ │ Content │ │
│ │ Tools │ │ Tools │ │ Tools │ │
│ └─────────────┘ └─────────────┘ └─────────────┘ │
└─────────────────────────────────────────────────────────────┘
│
┌─────────────────────────────────────────────────────────────┐
│ Provider Layer │
│ ┌─────────┐ ┌─────────┐ ┌───────────┐ ┌────────┐ ┌──────┐ │
│ │ OpenAI │ │ Ollama │ │OpenRouter │ │ n8n │ │Custom│ │
│ └─────────┘ └─────────┘ └───────────┘ └────────┘ └──────┘ │
└─────────────────────────────────────────────────────────────┘
import { MasterOrchestrator, AnalyticsOrchestrator } from '@/lib/agents';
// Create a master orchestrator
const master = new MasterOrchestrator({
id: 'master-1',
name: 'Task Coordinator',
description: 'Main orchestrator for complex tasks',
role: 'master_orchestrator',
domain: 'general',
model: 'gpt-4o',
});
// Execute a task
const result = await master.execute('Analyze Q4 sales and create a report');
// src/lib/agents/tools/custom.ts
import { Tool } from '@/lib/agents/core/types';
export const customTool: Tool = {
definition: {
name: 'my_custom_tool',
description: 'Does something specific',
parameters: {
input: {
type: 'string',
description: 'Input parameter',
required: true,
},
},
},
execute: async (params) => {
// Your custom logic here
return {
success: true,
data: { result: 'Processed: ' + params.input },
};
},
};
| Endpoint | Method | Description |
|---|---|---|
/api/agents | POST | Execute master orchestrator |
/api/agents/analytics | POST | Execute analytics agent |
/api/agents/research | POST | Execute research agent |
/api/agents/content | POST | Execute content agent |
/api/settings | GET/POST | Manage provider settings |
# Execute a task
curl -X POST http://localhost:3000/api/agents \
-H "Content-Type: application/json" \
-d '{
"message": "Analyze the latest market trends",
"context": { "industry": "technology" }
}'
src/
├── app/ # Next.js App Router
│ ├── api/ # API Routes
│ │ ├── agents/ # Agent endpoints
│ │ │ ├── route.ts # Master orchestrator
│ │ │ ├── analytics/ # Analytics agent
│ │ │ ├── research/ # Research agent
│ │ │ └── content/ # Content agent
│ │ └── settings/ # Settings management
│ ├── layout.tsx # Root layout
│ ├── page.tsx # Main entry (Landing → App)
│ └── globals.css # Global styles
│
├── components/
│ ├── ui/ # shadcn/ui components
│ ├── builder/ # Visual builder components
│ │ └── VisualBuilder.tsx # Main canvas component
│ ├── landing/ # Landing page components
│ │ ├── LandingPage.tsx # Marketing page
│ │ └── ThemeProvider.tsx # Dark/light theme
│ ├── MainApp.tsx # Main application
│ ├── PageWrapper.tsx # Page wrapper with providers
│ └── SettingsDialog.tsx # Settings modal
│
├── lib/
│ ├── agents/ # Agent system core
│ │ ├── core/ # Base classes and types
│ │ │ ├── Agent.ts # Base agent class
│ │ │ ├── Orchestrator.ts # Orchestrator base
│ │ │ └── types.ts # Type definitions
│ │ ├── orchestrators/ # Specialized orchestrators
│ │ │ ├── MasterOrchestrator.ts
│ │ │ ├── AnalyticsOrchestrator.ts
│ │ │ ├── ResearchOrchestrator.ts
│ │ │ └── ContentOrchestrator.ts
│ │ ├── providers/ # AI provider implementations
│ │ │ ├── types.ts # Provider types
│ │ │ ├── store.ts # Settings store
│ │ │ ├── OpenAIProvider.ts
│ │ │ ├── OllamaProvider.ts
│ │ │ ├── OpenRouterProvider.ts
│ │ │ ├── N8nProvider.ts
│ │ │ ├── AgentRouterProvider.ts
│ │ │ └── CustomProvider.ts
│ │ └── tools/ # Built-in tools
│ │ ├── analytics.ts # Analytics tools
│ │ ├── research.ts # Research tools
│ │ └── content.ts # Content tools
│ │
│ ├── builder/ # Visual builder core
│ │ ├── types.ts # Builder types
│ │ ├── store.ts # Builder state
│ │ ├── codeGenerator.ts # Visual → Code
│ │ └── nodes/ # Custom ReactFlow nodes
│ │
│ ├── db.ts # Database client
│ └── utils.ts # Utility functions
│
└── hooks/ # Custom React hooks
├── use-mobile.ts
└── use-toast.ts
# Dockerfile
FROM oven/bun:1 AS base
WORKDIR /app
# Install dependencies
COPY package.json bun.lock ./
RUN bun install --frozen-lockfile
# Copy source
COPY . .
# Build
RUN bun run build
# Expose port
EXPOSE 3000
# Start
CMD ["bun", "start"]
docker build -t multi-agent-system .
docker run -p 3000:3000 multi-agent-system
We welcome contributions! Please see our Contributing Guide for details.
# Clone and install
git clone https://github.com/yourusername/multi-agent-system.git
cd multi-agent-system
bun install
# Run development server
bun run dev
# Run linting
bun run lint
# Build for production
bun run build
| Script | Description |
|---|---|
bun run dev | Start development server |
bun run build | Build for production |
bun run start | Start production server |
bun run lint | Run ESLint |
bun run db:push | Push Prisma schema |
bun run db:generate | Generate Prisma client |
This project is licensed under the MIT License - see the LICENSE file for details.
Selected from shared topics, language and repository description—not editorial ratings.
AppajiDheeraj /
Meet.AI is a powerful, full-stack AI platform designed to help users create, manage, and interact with custom AI agents in seconds. From secure authentication to AI-powered meeting assistants, Meet.AI blends advanced technologies into an intuitive, production-ready app.