Project Info
This project did not submit a demo video on Devpost.
Inspiration
“What if AI could become your full-stack marketing and analytics team—on-demand, affordable, and intelligent?” We were inspired by the struggles that solo entrepreneurs, small business owners, and lean startup teams face in trying to build a strong marketing presence (italic) and understand their performance metrics. Hiring experts is expensive—and tools are often complex or disconnected. So, we set out to build a multimodal AI-powered platform that bridges content creation, brand strategy, and professional analytics, all in one place. What It Does MarketForge AI is a next-gen platform that uses agent-based architecture and multimodal inputs to: 🤖 Analyze your business type and goals using a smart Manager Agent ✍️ Generate personalized marketing content: captions, ads, slogans, emails 🎨 Support branding with design prompts and visual inspiration 📊 Deliver pro-grade analytics including: Conversion rates User engagement metrics Traffic heatmaps Market and trend analysis 🧠 Visualize insights using dynamic, AI-generated roadmap diagrams 💬 Conversational interface lets users ask anything, refine strategy, or get instant insights 🔄 All done automatically, with no need for a marketing or data team How We Built It Backend: Built with Flask to serve as a lightweight, scalable API layer Agents: Used Fetch.ai uAgents to power agent-based collaboration Frontend: Developed in React + Next.js, including: React Flow for dynamic visual roadmap generation KPI dashboard with real-time data Chat UI for conversational interaction Analytics Engine: Fetches business-specific metrics Auto-generates insights from user behavior MongoDB: Stores user data and agent interactions Challenges We Faced Synchronizing multiple AI agents Building an analytics engine that is both powerful and understandable Mapping user language to structured agent workflows Real-time updates in frontend diagrams Securing communication between all services What We Learned Agent-based systems are extremely powerful for modular and adaptive AI workflows Professional analytics can be democratized with the right UI and smart defaults A multimodal pipeline (text, logic, data, visuals) creates rich user experiences Simplicity and transparency matter—especially for small business owners What’s Next Implement Gemini and analytics engine Dynamic roadmap flowcharts from AI Add voice interaction via Vapi Auto-generate PDF marketing reports Deeper market intelligence features Personalized growth suggestions over time 🧰 Built With
🚀 MarketForgeAI
MarketForgeAI is an intelligent AI-driven platform that empowers businesses—ranging from solo entrepreneurs to large enterprises—to supercharge their content creation, marketing strategies, and promotional efforts. It acts as a virtual growth assistant, orchestrating powerful AI agents to streamline workflows, analyze data, and execute personalized campaigns.
👥 Team
Authors
-
Shokhabbos Mukhammatov - Backend Engineer
- GitHub: @shokhabbos-mukhammatov
-
Akmal Shovkatov - Frontend Developer & UI/UX Designer
- GitHub: @akmal-shovkatov
-
Muzaffar Muratov - Machine Learning Engineer
- GitHub: @muzaffar-muratov
🔧 Tech Stack
Frontend
- Next.js
- Tailwind CSS
- React Hooks
- TypeScript
Backend
- Flask
- Python 3.10+
- Integration with Fetch.ai via
uAgents - Grok
- ASI:1
- Agent orchestration system
- RESTful API
📁 Project Structure
MarketForgeAI/
├── backend/ # Flask server and agent logic
│ ├── agents/ # AI agent clients (Fetch, ASI:1, etc.)
│ ├── utils/ # Environment and shared utilities
│ ├── app.py # Entrypoint for Flask server
│ ├── routes.py # API endpoints (e.g., /ask, /agents/register)
│ └── requirements.txt # Python dependencies
│
├── frontend/ # Next.js + Tailwind UI
│ ├── app/ # Route-based pages (chat, landing, analyze, etc.)
│ ├── components.json # Frontend components registry
│ └── tailwind.config.ts # Tailwind setup
│
└── README.md # You're here!
⚙️ Setup Instructions
Prerequisites
- Node.js 18+
- Python 3.10+
- Git
- Virtualenv (optional but recommended)
1. Backend (Flask + uAgents)
cd backend
python -m venv .venv
source .venv/bin/activate # or .venv\Scripts\activate on Windows
pip install -r requirements.txt
# Set required environment variables
export AGENTVERSE_API_KEY=your_key_here # or use .env loader
# Run the API
uvicorn app:app --reload
💡 Make sure your Fetch.ai Agentverse API key is valid.
2. Frontend (Next.js)
cd frontend
npm install
npm run dev
Frontend will start at: http://localhost:3000
🧠 Core Features
- ✅ AI Chat powered by Gemini / Fetch
- ✅ Roadmap UI with dynamic diagram manipulation
- ✅ Company profile analyzer
- ✅ KPI dashboard and real-time analytics (planned)
- ✅ Agent orchestration via Flask
- ✅ Modular plugin-like agent architecture
- ✅ Ready-to-use demo mode
💡 Agent Integrations
- Manager Agent: Coordinates all AI services and business logic.
- Trend Detector: Detects marketing trends based on user domain.
- ASI:One Client: For chat completions via Fetch.ai.
- AgentVerse Integration: For stateful agent handling.
📌 Routes Overview
Frontend Routes
| URL Path | Description |
|---|---|
/ | Landing page with login/demo |
/app/chat | Main chatbot with dynamic logic |
/app/roadmap | AI-powered roadmap and diagram UI |
/app/analyze | Business analysis and recommendation |
/app/company-details | Company setup and input |
API Endpoints (Backend)
| Endpoint | Description |
|---|---|
POST /api/ask | Handles AI conversation requests |
POST /api/agents/register | Registers a new agent |
POST /api/agents/chat | Sends a message to an agent |
🧪 Testing
# Run backend tests
cd backend
pytest tests.py
Frontend testing setup TBD.
🤝 Contributing
PRs are welcome! Please follow these steps:
- Fork the repo
- Create a new branch (
git checkout -b feature/xyz) - Commit your changes (
git commit -am 'Add xyz feature') - Push to the branch (
git push origin feature/xyz) - Create a pull request
🧠 Inspiration
This project is part of the UC Berkeley AI Hackathon 2025, supported by sponsors like Fetch.ai, Groq, Claude (Anthropic), and Letta.
Analysis
View
Metric
- 14
- 10
- 7
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- CSSIn code
- FlaskIn code
- JavaScriptIn code
- Next.jsIn code
- PythonIn code
- ReactIn code
- Tailwind CSSIn code
- TypeScriptIn code
- MongoDBClaimed
8 of 9 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
327 KB
Source files
76
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
shokhabbos-mukhammatov/MarketForgeAI
90 files · 2.7 MB · @ f0df441
Structure
Interface
58 files · 64%Screens, components and styles rendered to the user.
Application logic
15 files · 17%Domain rules, services and shared utilities.
+1 more
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- TypeScript79%
- Python18%
- Markdown3%
- CSS1%
- JavaScript0%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
frontend/package.json
npm · 61- @hookform/resolvers
- @next/swc-wasm-nodejs
- @radix-ui/react-accordion
- @radix-ui/react-alert-dialog
- @radix-ui/react-aspect-ratio
- @radix-ui/react-avatar
- @radix-ui/react-checkbox
- @radix-ui/react-collapsible
- @radix-ui/react-context-menu
- @radix-ui/react-dialog
- @radix-ui/react-dropdown-menu
- @radix-ui/react-hover-card
- @radix-ui/react-label
- @radix-ui/react-menubar
- @radix-ui/react-navigation-menu
- @radix-ui/react-popover
- @radix-ui/react-progress
- @radix-ui/react-radio-group
- +43 more
backend/requirements.txt
pypi · 8- asyncio
- fetchai
- flask
- flask_cors
- pydantic
- python-dotenv
- requests
- uagents
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.