Installing & Running Tharior Remedai

Deploy the Tharior Remedai Agentic Gateway on your local machine, via Docker, or onto an enterprise Kubernetes cluster with KEDA and HPA operators.

1. Prerequisites

• Python: Version 3.10+ (3.11 recommended)
• Anvesh: Vector & Knowledge Graph Engine (runs in embedded or remote mode)
• Kubernetes: (Optional) v1.28+ for HPA & KEDA deployments
• LLM Key: OpenRouter API key (Gateway Route) or direct provider keys (OpenAI, Anthropic, Gemini)

2. Local Monorepo Setup

Clone the repository, initialize the Python virtual environment, and install dependencies:

# 1. Clone repository
git clone https://github.com/vaagatech/tharior-remedai.git
cd autonomous-coding-engineer

# 2. Setup Python environment & backend dependencies
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# 3. Install frontend workspace dependencies
npm install

# 4. Verify test suite (all 62 tests)
.venv/bin/pytest tests

3. Starting the Monorepo Services

Start the API Gateway backend, Web Desk frontend, and documentation server:

# Terminal 1: FastAPI Gateway (port 8000)
npm run dev:api

# Terminal 2: React + Vite Web Desk (port 5173)
npm run dev:web

# Terminal 3: Local Docs Site (port 8080)
npm run dev:docs

4. Deploying to Kubernetes (HPA & KEDA)

Deploy to Kubernetes with automated Horizontal Pod Autoscaling and KEDA event-driven scaling:

# 1. Apply Deployment & Config
kubectl apply -f k8s/configmap.yaml
kubectl apply -f k8s/deployment.yaml
kubectl apply -f k8s/service.yaml

# 2. Apply HPA (CPU/Memory scaling) & KEDA (Workload queue scaling)
kubectl apply -f k8s/hpa.yaml
kubectl apply -f k8s/keda-scaledobject.yaml
kubectl apply -f k8s/keda-scaledjob.yaml