Installation

Every way to run llmBreakr — pre-built images, Docker Compose, or a local development setup.

Pick whichever matches how you deploy everything else.

Pre-built image (recommended)

Published on Docker Hub and GHCR — no local build step.

docker pull yashbansal0412/llmbreakr-ai-gateway:latest

Then run it with your .env:

docker run -d \
  --env-file .env \
  -p 4000:4000 \
  -p 3000:3000 \
  yashbansal0412/llmbreakr-ai-gateway:latest

git clone https://github.com/yashb007/llmBreakr-ai-gateway.git
cd llmBreakr-ai-gateway
cp server/.env.example .env
docker compose up --build

Or skip the build and use the published image with a pinned tag:

IMAGE_TAG=1.0.2 docker compose up -d

For working on llmBreakr itself, or running it without containers.

cd server
npm install
cp .env.example .env
# edit .env, then:
npm run dev

Requires Node.js 18+, a reachable MySQL instance, and Redis.

Component	Port	Purpose
Gateway + admin API	`4000`	`/api/data` (LLM proxy) and `/api/admin` (config, audit)
Management dashboard	`3000`	Next.js UI for keys, projects, and monitoring

Both ship from the same container in the production image — one deployable to manage.