Skip to content

rkgovindu/Discovery

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AI Agent Registry & Discovery Portal

A production-grade platform for registering, discovering, and managing AI agents and tools within an organization. Includes a Hackathon & Idea Management Module with dual entry paths (hackathon ideas → tool promotion, and direct tool submission).

Architecture

├── backend/          # FastAPI (Python 3.12)
├── frontend/         # Next.js 14 + Tailwind CSS
├── database/         # PostgreSQL schema & seed data
└── docker-compose.yml

Features

Tool Registry

  • Submit, search, and discover AI tools with full metadata
  • Multi-stage approval pipeline (Domain → Risk → Tech)
  • AI-powered tag suggestions
  • Duplicate/similar tool detection
  • Comments and interest tracking
  • Version history with snapshots

Hackathon & Idea Management

  • Dual entry system: Submit Ideas (hackathon path) or Submit Tools (direct path)
  • Hackathon lifecycle: Draft → Open → Judging → Closed
  • Idea submission with team members, duplicate checking
  • Hackathon submissions with screenshots
  • Promote submission → Tool with one click (auto-fills from idea data)
  • Source-wise analytics tracking conversion rates

Dashboard & Analytics

  • KPI cards: total tools, ideas, hackathons, conversion rates
  • Tools by source (hackathon vs direct vs external)
  • Approval pipeline status
  • Source → production conversion rates
  • Top domains

Admin Panel

  • User management with role assignment (viewer/submitter/reviewer/admin)
  • Domain & tag CRUD
  • Audit log

Quick Start

Docker (Recommended)

cd AgentsDiscovery

# Start all services
docker compose up --build

# Access:
#   Frontend:  http://localhost:3000
#   Backend:   http://localhost:8000
#   API Docs:  http://localhost:8000/docs

Manual Setup

1. Database

# Create PostgreSQL database
createdb agent_registry
psql agent_registry < database/schema.sql

2. Backend

cd backend
python -m venv venv
venv\Scripts\activate        # Windows
# source venv/bin/activate   # Linux/Mac

pip install -r requirements.txt

# Set environment variables
set DATABASE_URL=postgresql://user:pass@localhost:5432/agent_registry
set SECRET_KEY=your-secret-key

uvicorn app.main:app --reload --port 8000

3. Frontend

cd frontend
npm install
npm run dev
# Opens at http://localhost:3000

API Overview

Endpoint Description
POST /api/auth/register Register user
POST /api/auth/login Login (OAuth2 form)
GET /api/tools List/search tools
POST /api/tools Submit new tool
GET /api/tools/{id}/similar Find similar tools
POST /api/approvals/{tool_id}/{stage} Process approval
GET /api/dashboard/stats Dashboard KPIs
POST /api/hackathons Create hackathon
POST /api/ideas Submit idea
GET /api/ideas/check-duplicates Check for duplicate ideas
POST /api/submissions Create hackathon submission
POST /api/submissions/{id}/promote Promote submission → tool
GET /api/hackathons/analytics/summary Hackathon analytics
GET /api/admin/audit-log Audit log

Full interactive docs at /docs (Swagger) or /redoc.

Tech Stack

Backend: FastAPI, SQLAlchemy 2.0, PostgreSQL, JWT auth, Pydantic v2
Frontend: Next.js 14, React 18, Tailwind CSS, Recharts, Lucide Icons
Deployment: Docker Compose with PostgreSQL

Environment Variables

Variable Default Description
DATABASE_URL (required) PostgreSQL connection string
SECRET_KEY (required) JWT signing key
CORS_ORIGINS ["http://localhost:3000"] Allowed CORS origins
NEXT_PUBLIC_API_URL /api Backend API URL for frontend

About

internal AI discovery + governance platform—think lightweight AI marketplace + workflow engine + registry.

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors