Skip to content

mlengineershub/sherlock

Repository files navigation

SecAI Investigation Agent

A modern security breach investigation tool with an interactive visualization interface.

Features

  • Interactive investigation tree visualization
  • AI-powered hypothesis generation
  • Node expansion for deeper investigation
  • Detailed node information view
  • Investigation report generation
  • Modern, responsive UI

Project Structure

  • frontend/: React-based frontend application
  • backend/: Python-based backend services
    • common/: Shared utilities and services
    • investigation/: Investigation agent and tree management

Running the Application

Backend

  1. Start the backend API server:
python -m backend.investigation.run_api

The API server will run on http://localhost:8000

Frontend

  1. Navigate to the frontend directory:
cd frontend
  1. Install dependencies:
npm install
  1. Start the development server:
npm run dev

The frontend will be available at http://localhost:5173

Usage

  1. Enter initial breach information in the text area
  2. Click "Start Investigation" to generate the initial investigation tree
  3. Interact with nodes:
    • Click "View Details" to see detailed information about a node
    • Click "Expand" to generate more hypotheses based on the selected node
    • Click "Plausible" to mark a node as plausible and automatically expand it
    • Click "Implausible" to mark a node as implausible and lock it
  4. Click "Generate Report" to create a comprehensive investigation report

Technologies Used

  • Frontend: React, Vite, react-d3-tree
  • Backend: Python, FastAPI, AWS Bedrock (Claude AI models)

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •