Skip to content
2nd Place

ForenSight AI

ForenSight AI is a multimodal “AI detective” that lets you upload scene photos, videos, audio clips, and witness statements - and instantly generates a unified, AI-reasoned reconstruction of what likely happened.

Code Cerebral Valley

Core trick

Gemini 3 cross-references evidence from photos, video frames, audio, and statements to build timelines and flag contradictions, then renders scenario images.

Tags

legalvision

Description

ForenSight AI is a multimodal “AI detective” that lets you upload scene photos, videos, audio clips, and witness statements - and instantly generates a unified, AI-reasoned reconstruction of what likely happened. Gemini 3 analyzes every piece of evidence, builds timelines, finds contradictions, and proposes multiple plausible scenarios, while Nano Banana Pro generates high-resolution 2K/4K visual reconstructions from those scenarios. The goal was to explore how far multi-modelity can go when reasoning (Gemini 3) and rendering (Nano Banana Pro) are fused into one interactive forensic experience.
Aadhithr/ForenSight★ 22 forksTypeScriptCreated Dec 7, 2025 · last push Dec 11, 2025

README excerpt

# ForenSight AI

Multimodal AI forensic analysis platform for scene reconstruction and evidence reasoning.
https://youtu.be/Ip_bJENt94Y

## Prerequisites

- Node.js 18+ and npm
- **ffmpeg** (required for video frame extraction)
  - macOS: `brew install ffmpeg`
  - Linux: `sudo apt-get install ffmpeg` or `sudo yum install ffmpeg`
  - Windows: Download from [ffmpeg.org](https://ffmpeg.org/download.html)

## Setup & Running

### Quick Start

1. Install all dependencies:
   ```bash
   npm run install:all
   ```

2. **Backend Setup:**
   ```bash
   cd backend
   cp .env.example .env
   # Edit .env and add your GEMINI_API_KEY
   npm run dev
   ```

3. **Frontend Setup (in a new terminal):**
   ```bash
   cd frontend
   cp .env.local.example .env.local
   # Edit .env.local if needed (default should work)
   npm run dev
   ```

4. Open [http://localhost:3000](http://localhost:3000) in your browser

### Backend Details

1. Navigate to `backend/` directory
2. Install dependencies:
   ```bash
   npm install
   ```
3. Copy `.env.example` to `.env` and add your API keys:
   ```env
   GEMINI_API_KEY=your_gemini_api_key_here
   NANO_BANANA_API_KEY=your_key_here (optional for now)
   NANO_BANANA_API_URL=https://api.nanobanana.com (optional)
   ```
4. Start the server:
   ```bash
   npm run dev
   ```
   Server runs on http://localhost:3001

### Frontend Details

1. Navigate to `frontend/` directory
2. Install dependencies:
   ```bash
   npm install
   ```
3. Copy `.env.local.example` to `.en

Team