PATTY GitHub Details, Stars and Alternatives | OpenRepoFinder
Dessiidoo / repository
PATTY
Production-ready, self-hostable AI chat assistant platform — TypeScript monorepo with persistent PostgreSQL conversation history, OpenAI-compatible model support, API-key-authenticated Express backend, Docker deployment, and extensible GitHub and email integrations. Ship a branded AI assistant product in days.
A transparent discovery signal based on current public GitHub metadata.
Recent activity35% weight
100
Community adoption25% weight
0
Maintenance state20% weight
40
License clarity10% weight
0
Project information10% weight
100
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
README preview
PATTY — Cognitive Buddy
A production-ready, self-hostable AI chat assistant platform with persistent conversation history, OpenAI-compatible model support, and extensible GitHub/email integrations — deployable in minutes, brandable in hours.
Overview
PATTY (also called Cognitive Buddy) is a full-stack AI chat assistant application built for teams and builders who want a working, deployable product — not another proof-of-concept. It ships with a polished React/TypeScript frontend, a secured Express.js API backend, PostgreSQL-backed persistent conversation history, and Docker-based deployment. It connects to any OpenAI-compatible model endpoint, meaning you can run it against GPT-4o, Claude via proxy, local Ollama models, or any other OpenAI-spec-compatible API.
Unlike throwaway chatbot demos, PATTY is a complete SaaS skeleton. A business can white-label it, extend it, and ship it to real users in days — not months. The shadcn/ui component library delivers a polished, accessible frontend out of the box, and the API-key-authenticated backend makes it ready for multi-tenant or enterprise deployments with minimal additional work.
Key Features
Persistent Conversation History — All chat sessions are stored in PostgreSQL via Drizzle ORM. Users pick up exactly where they left off across sessions and devices.
OpenAI-Compatible Model Support — Plug in any OpenAI-spec API endpoint: GPT-4o, GPT-3.5, self-hosted Ollama, LM Studio, or any compatible proxy. No vendor lock-in.
API-Key Authentication — Backend routes are protected via BUDDY_API_KEY, making it straightforward to secure multi-user or white-label deployments.
Professional shadcn/ui Frontend — Built on Radix UI primitives with Tailwind CSS. Dark/light mode ready. Immediately presentable to end users or clients.
Docker Containerized — Comes with a production-ready Dockerfile and Docker Compose support for one-command local and cloud deployment.
GitHub Integration Ready — @octokit/rest dependency included, enabling GitHub-connected workflows such as issue creation from chat, repo summaries, or developer-assistant tooling.
Email Notification Layer — nodemailer dependency included for transactional email notifications — conversation summaries, alerts, or user onboarding flows.
Replit-Native Deployment — .replit config included for instant cloud deployment without any local infrastructure setup.
TypeScript Monorepo — Clean, typed codebase with shared types across client and server, reducing integration bugs and making extension safe and predictable
The React frontend sends user messages to the Express backend via authenticated REST calls.
The backend persists the message to PostgreSQL, then forwards the full conversation context to the configured OpenAI-compatible model API.
The model's response is stored and returned to the frontend, which renders it in the chat thread.
GitHub and email integrations can be triggered from backend logic to extend the assistant's capabilities beyond simple Q&A.
Installation & Setup
Prerequisites
Node.js 18+
PostgreSQL 14+ (or Docker)
An OpenAI API key or any OpenAI-compatible endpoint
1. Clone the Repository
git clone https://github.com/Dessiidoo/PATTY.git
cd PATTY
2. Configure Environment Variables
Copy the example environment file and fill in your values:
cp .env.example .env
Key variables to configure:
Variable
Description
Required
DATABASE_URL
PostgreSQL connection string
✅
OPENAI_API_KEY
OpenAI or compatible model API key
✅
BUDDY_API_KEY
Secret key to authenticate backend API requests
✅
OPENAI_BASE_URL
Override for custom/self-hosted model endpoint
Optional
PORT
Backend server port (default: 5000)
Optional
SMTP_HOST
Mail server host for nodemailer
Optional
SMTP_PORT
Mail server port
Optional
SMTP_USER
SMTP authentication username
Optional
SMTP_PASS
SMTP authentication password
Optional
GITHUB_TOKEN
GitHub personal access token for Octokit integration
Optional
3a. Docker Deployment (Recommended)
docker compose up --build
This spins up the app and a PostgreSQL instance. See DEPLOYMENT.md for full Docker Compose configuration details.
3b. Manual Local Development
# Install dependencies
npm install
# Push the database schema
npm run db:push
# Start the development server (client + server concurrently)
npm run dev
The app will be available at http://localhost:5173 (frontend) with the API running on http://localhost:5000.
3c. Replit Deployment
Import the repo directly into Replit. The .replit configuration is pre-set. Add your environment variables in the Replit Secrets panel and click Run.
API Overview
All API routes are prefixed with /api and authenticated via the BUDDY_API_KEY header.
Authorization: Bearer <BUDDY_API_KEY>
Method
Endpoint
Description
GET
/api/sessions
List all chat sessions
POST
/api/sessions
Create a new chat session
GET
/api/sessions/:id/messages
Retrieve message history for a session
POST
/api/chat
Send a message and receive an AI response
DELETE
/api/sessions/:id
Delete a session and its messages
See DEPLOYMENT.md for detailed request/response shapes and authentication examples.
Usage
Open the app in your browser.
Start a new conversation from the sidebar.
Type a message — PATTY responds using your configured model.
Conversations persist automatically; return to any previous session at any time.
Access settings to configure the model, persona, or API endpoint at runtime.
Why This Exists
Building a production-ready AI chat assistant from scratch is not a weekend project. You need a typed full-stack architecture, a persistent data layer, authenticated APIs, a professional UI component system, containerized deployment, and integration hooks for the services your business actually uses (email, GitHub, etc.).
Most open-source chatbot projects are either over-engineered research frameworks or bare-minimum demos. PATTY is neither — it is a deployable product skeleton at the right level of abstraction: enough infrastructure to be real, not so much that you are locked into decisions you did not make. A development team can fork it, brand it, and ship a product to paying customers in days.
