Skip to content

dpk-smartcoder/AlgoForge

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 

Repository files navigation

AlgoForge

Python Docker React TailwindCSS TypeScript FastAPI C++ Java Firebase OpenAI GPT-4 Google Gemini AutoGen




AlgoForge is an end-to-end platform for algorithm problem solving, AI-powered code generation, and solution analysis.
It combines a modern React frontend with a FastAPI backend, orchestrated by agentic AI for multi-language code generation, complexity analysis, and Firebase-based user management.

Watch Demo Video


Features

  • AI-powered code generation (Python, Java, C++).
  • Multi-agent pipeline for problem extraction, solution generation, and code fitting.
  • Automatic time/space complexity analysis and solution explanation.
  • User authentication via Firebase.
  • Problem history tracking and solution review.
  • Modern, responsive UI with dark mode support.

Architecture

  • Frontend: React + TypeScript + Tailwind CSS (frontend/)
  • Backend: FastAPI + SQLAlchemy + Firebase Admin + Agentic AI (backend/)
  • AI Pipeline: Multi-agent orchestration for extraction, solution, and fitting (backend/app/agentic_ai/)

Tech Stack


Frontend

  • Built with Create React App
  • Styled using Tailwind CSS with custom scrollbars
  • Firebase authentication + storage
  • Key files:
    • src/App.tsx → Main app and routing
    • src/pages/ProblemResult.tsx → Solution display
    • src/services/api.ts → API integration

Start Frontend

cd frontend
npm install
npm start


Runs at [http://localhost:3000](http://localhost:3000).

---

## Backend

- Built with [FastAPI](https://fastapi.tiangolo.com/)
- Uses [SQLAlchemy](https://www.sqlalchemy.org/) for database ORM
- Firebase Admin SDK for user authentication
- Agentic AI pipeline for code extraction, solution, and fitting
- Key files:
  - `app/__init__.py`: FastAPI app, models, routes
  - `app/agentic_ai/final.py`: Pipeline orchestrator
  - `app/agentic_ai/ThreeAgentTeam.py`: Multi-agent solution generator

### Start Backend

```sh
cd backend
python -m uvicorn app.main:app --reload

Runs at http://localhost:8000.


Environment Variables

Frontend (frontend/.env)

REACT_APP_FIREBASE_API_KEY=...
REACT_APP_FIREBASE_AUTH_DOMAIN=...
REACT_APP_FIREBASE_PROJECT_ID=...
REACT_APP_FIREBASE_STORAGE_BUCKET=...
REACT_APP_FIREBASE_SENDER_ID=...
REACT_APP_FIREBASE_APP_ID=...
REACT_APP_API_BASE=http://localhost:8000

Backend (backend/.env)

ALGOFORGE_DB=sqlite:///./algoforge.db
key4=...         # AI model API key
model4=...       # AI model name
# Add other agent keys/models as needed

Project Structure

AlgoForge/
  frontend/
    src/
      App.tsx
      pages/
        ProblemResult.tsx
      services/
        api.ts
    public/
    tailwind.config.js
    ...
  backend/
    app/
      __init__.py
      main.py
      agentic_ai/
        final.py
        ThreeAgentTeam.py
        ...
    requirements.txt
    Dockerfile
    ...

Running the Project

  1. Clone the repository

    git clone https://github.com/LallerLavish/AlgoForge.git
    cd AlgoForge
  2. Setup environment variables
    Copy .env.example to .env in both frontend/ and backend/ and fill in your credentials.

  3. Install dependencies and start backend

    cd backend
    pip install -r requirements.txt
    python -m uvicorn app.main:app --reload
  4. Install dependencies and start frontend

    cd frontend
    npm install
    npm start
  5. Access the app


Contributing

Pull requests are welcome! For major changes, please open an issue first to discuss what you would like to change.


*Crafted with ❤️ by Lavish and Deepak.

About

AlgoForge is a multi-agentic AI system for solving complex DSA problems by mimicking human strategies. Using OpenAI, Gemini, and AutoGen, it enables collaborative agents to refine solutions with 3x efficiency over single models. Built with React, Tailwind, TypeScript, FastAPI, and Firebase, it delivers low-latency, human-aligned problem solving.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors