Spaces:

fairleap-ai
/

README

Running

File size: 9,867 Bytes

---
title: Fairleap AI
emoji: 🛵
colorFrom: green
colorTo: blue
sdk: static
pinned: false
short_description: AI co-pilot for Indonesia's gig drivers
models:
  - fairleap-ai/fairleap-v1-clm-qwen3.5-4b-adapter
  - fairleap-ai/fairleap-v1-clm-sahabatai-8b-adapter
datasets:
  - fairleap-ai/fairleap-driver-chat-sft-43k
---

<div align="center">
  <table border="1">
    <tr>
      <td align="center" style="padding: 20px;">
        <h3>📢 Domain & Email Migration Notice</h3>
        <p>From <b>May 24 th, 2026</b>, Fairleap AI will transition to new domains as <code>fairleap.cloud</code> will not be renewed:</p>
        <p>🌐 <b>Website:</b> <a href="https://fairleap.faizath.com">fairleap.faizath.com</a> (formerly <i>fairleap.cloud</i>)<br>
        ⚙️ <b>API:</b> <a href="https://fairleap-api.faizath.com">fairleap-api.faizath.com</a> (formerly <i>api.fairleap.cloud</i>)<br>
        📧 <b>Email:</b> <a href="mailto:contact@fairleap.faizath.com">contact@fairleap.faizath.com</a> (formerly <i>contact@fairleap.cloud</i>)<br>
        🛰️ <b>CDN:</b> <a>fairleap-cdn.faizath.com</a> (formerly <i>cdn.fairleap.cloud</i>)<br>
        📈 <b>Status Pages:</b> <a href="https://status.faizath.com/status/fairleap">https://status.faizath.com/status/fairleap</a> (formerly <i>status.fairleap.cloud</i>)
        </p>
      </td>
    </tr>
  </table>
</div>

<p align="center">
  <img src="profile/assets/logo.png"/>
  <h1 align="center">Fairleap AI</h1>
</p>

<p align="center">
  <b>An AI co-pilot for the financial well-being of Indonesia's gig drivers.</b>
</p>

## 📘 What is Fairleap AI?

**Fairleap AI** is an AI-powered financial well-being platform built for **Gojek / GoTo ride-hailing and delivery drivers**. It turns a driver's raw, irregular trip data into clear earnings insights, personalized financial guidance, and wellness support — helping drivers move from day-to-day income uncertainty toward long-term financial stability.

The name says it all: a **fair leap** forward for the gig workers who keep Indonesia moving.

## 🏆 Alibaba Cloud Indonesia GenAI Hackathon 2025

<p align="center">
  <b>🥇 Fairleap AI was built and submitted to the Alibaba Cloud Indonesia GenAI Hackathon 2025, where it was selected as a <ins>Top 12 Finalist</ins>.</b>
</p>

The **Alibaba Cloud Indonesia GenAI Hackathon 2025** is a national-scale Generative AI hackathon held on **May 24–25, 2025 in Jakarta, Indonesia** (Habitate, Kuningan). It is **organized by Alibaba Cloud, the GoTo Group, and KOMDIGI** (Indonesia's Ministry of Communication and Digital Affairs).

The competition challenges innovators across Indonesia to build impactful, real-world solutions using **Generative AI on Alibaba Cloud** — leveraging services such as the **Qwen** large language models via **DashScope**. It brings together developers, students, and startups to prototype GenAI applications that address tangible problems, with finalists pitching their solutions to a panel of industry judges.

Out of all participating teams, **Fairleap AI advanced to the Top 12 Finalists**, recognizing its use of Generative AI to tackle income uncertainty and well-being for Indonesia's gig-economy drivers.

## 🎬 Presentation & Demo Video

<p align="center">
  <a href="https://drive.google.com/file/d/1vIrcJjZzXG86FMHDdO9DP4x_Eg0us74s/preview">
    <img src="profile/assets/demo.gif" alt="Watch the Fairleap AI presentation & demo video" width="100%"/>
  </a>
</p>

## 🖼️ Screenshots

<p align="center">
  <table>
    <tr>
      <td><img src="profile/assets/screenshots/1.png"/></td>
      <td><img src="profile/assets/screenshots/2.png"/></td>
      <td><img src="profile/assets/screenshots/3.png"/></td>
    </tr>
    <tr>
      <td><img src="profile/assets/screenshots/4.png"/></td>
      <td><img src="profile/assets/screenshots/5.png"/></td>
      <td><img src="profile/assets/screenshots/6.png"/></td>
    </tr>
    <tr>
      <td><img src="profile/assets/screenshots/7.png"/></td>
      <td><img src="profile/assets/screenshots/8.png"/></td>
      <td><img src="profile/assets/screenshots/9.png"/></td>
    </tr>
    <tr>
      <td><img src="profile/assets/screenshots/10.png"/></td>
      <td><img src="profile/assets/screenshots/11.png"/></td>
      <td><img src="profile/assets/screenshots/12.png"/></td>
    </tr>
    <tr>
      <td><img src="profile/assets/screenshots/13.png"/></td>
      <td><img src="profile/assets/screenshots/14.png"/></td>
      <td><img src="profile/assets/screenshots/15.png"/></td>
    </tr>
    <tr>
      <td><img src="profile/assets/screenshots/16.png"/></td>
      <td><img src="profile/assets/screenshots/17.png"/></td>
      <td><img src="profile/assets/screenshots/18.png"/></td>
    </tr>
    <tr>
      <td><img src="profile/assets/screenshots/19.png"/></td>
      <td><img src="profile/assets/screenshots/20.png"/></td>
      <td><img src="profile/assets/screenshots/21.png"/></td>
    </tr>
    <tr>
      <td><img src="profile/assets/screenshots/22.png"/></td>
      <td><img src="profile/assets/screenshots/23.png"/></td>
      <td><img src="profile/assets/screenshots/24.png"/></td>
    </tr>
    <tr>
      <td><img src="profile/assets/screenshots/25.png"/></td>
      <td><img src="profile/assets/screenshots/26.png"/></td>
      <td><img src="profile/assets/screenshots/27.png"/></td>
    </tr>
    <tr>
      <td><img src="profile/assets/screenshots/28.png"/></td>
      <td><img src="profile/assets/screenshots/29.png"/></td>
      <td><img src="profile/assets/screenshots/30.png"/></td>
    </tr>
  </table>
</p>

## ❓ The Problem

Gig-economy drivers are the backbone of Indonesia's on-demand economy, yet they face structural challenges that traditional financial tools ignore:

- **Income uncertainty** — earnings swing daily with demand, weather, surge pricing, and hours worked, making it nearly impossible to budget or plan ahead.
- **No financial visibility** — drivers rarely have tools to understand *why* they earn what they earn, or how to optimize their working hours.
- **Limited access to financial advice** — conventional financial advisory and investment products are not designed for variable, cash-based gig income.
- **Well-being is overlooked** — long hours on the road create fatigue and stress that directly affect both safety and earning capacity.

## 💡 How Fairleap AI Solves It

Fairleap AI combines **machine-learning forecasting** with **Generative AI (RAG-powered) advisory** to give every driver a personal financial and wellness assistant:

- **📊 Earnings Analytics & Forecasting** — ML regression models (XGBoost / scikit-learn) analyze historical trip data to surface earning patterns and **predict future earnings**, so drivers know what to expect and when to drive.
- **🤖 AI Financial Advisor** — a Generative AI advisor (powered by Alibaba Cloud Qwen via DashScope, with RAG grounding) delivers **personalized financial tips** tailored to each driver's income profile.
- **📈 Investment Guidance** — an AI investment bot recommends suitable, easy-to-understand investment options for variable gig income.
- **🧘 Wellness Companion** — an AI wellness assistant provides health, fatigue, and work-life-balance guidance to keep drivers safe and sustainable.
- **💬 Conversational Chatbot** — a RAG-based chatbot answers driver questions in natural language, grounded in Fairleap's domain knowledge.
- **🖥️ Unified Dashboard** — a clean web dashboard brings earnings, analytics, financial advice, and wellness together in one place.

## 🗂️ Repositories & Deployments

| Component | Description | Tech Stack | Repository | Deployment URL / Hugging Face Repo |
|-----------|-------------|------------|------------|------------------------------------|
| 🌐 **Frontend** | Next.js web app & driver dashboard | Next.js 15, React 19, TypeScript, Tailwind CSS, shadcn/ui, Recharts, GSAP | [Fairleap-AI/fairleap-fe](https://github.com/Fairleap-AI/fairleap-fe) | [fairleap.faizath.com](https://fairleap.faizath.com) *(formerly fairleap.cloud)* |
| ⚙️ **API Backend** | Core REST API, auth & data layer | Node.js, Express 4, MongoDB (Mongoose), JWT, Passport, Nodemailer, Docker | [Fairleap-AI/fairleap-api](https://github.com/Fairleap-AI/fairleap-api) | [fairleap-api.faizath.com](https://fairleap-api.faizath.com) *(formerly api.fairleap.cloud)* |
| 🧠 **AI / RAG Backend** | ML forecasting & GenAI advisory services | Python, Flask, Gunicorn, XGBoost, scikit-learn, pandas, NumPy, DashScope (Qwen) | [Fairleap-AI/fairleap-ai](https://github.com/Fairleap-AI/fairleap-ai) | Served with Docker internally |
| 📚 **SFT Dataset** | 42,743 synthetic Indonesian driver conversations | JSONL, Parquet, PyArrow, Hugging Face Datasets | [Fairleap-AI/fairleap-driver-chat-sft-43k](https://github.com/Fairleap-AI/fairleap-driver-chat-sft-43k) | [🤗 datasets/fairleap-ai/fairleap-driver-chat-sft-43k](https://huggingface.co/datasets/fairleap-ai/fairleap-driver-chat-sft-43k) |
| 🤖 **Qwen3.5-4B Adapter** | QLoRA adapter for driver chat & tool calling | PEFT (QLoRA), Unsloth, TRL, Transformers, bitsandbytes, PyTorch | [Fairleap-AI/fairleap-v1-clm-qwen3.5-4b-adapter](https://github.com/Fairleap-AI/fairleap-v1-clm-qwen3.5-4b-adapter) | [🤗 fairleap-ai/fairleap-v1-clm-qwen3.5-4b-adapter](https://huggingface.co/fairleap-ai/fairleap-v1-clm-qwen3.5-4b-adapter) |
| 🤖 **Sahabat-AI 8B Adapter** | QLoRA adapter on the Llama-3 Indonesian base | PEFT (QLoRA), Unsloth, TRL, Transformers, bitsandbytes, PyTorch | [Fairleap-AI/fairleap-v1-clm-sahabatai-8b-adapter](https://github.com/Fairleap-AI/fairleap-v1-clm-sahabatai-8b-adapter) | [🤗 fairleap-ai/fairleap-v1-clm-sahabatai-8b-adapter](https://huggingface.co/fairleap-ai/fairleap-v1-clm-sahabatai-8b-adapter) |

## 📝 License
This project is licensed under the MIT License.