Summary

Languine provides a self-hosted, Vercel-native solution for AI-powered application localization. Targeting developers, it simplifies the translation workflow by integrating a CLI tool with a managed Vercel deployment, offering a streamlined and efficient approach to internationalizing applications.

How It Works

The system leverages a Vercel-native architecture built with Next.js 16 (App Router) and Node.js. Translations are managed via a self-hosted CLI (npx languine@selfhosted) that communicates with a Vercel deployment. This deployment utilizes Serverless Postgres via Drizzle ORM for data persistence and Vercel Workflows for background job processing. AI translation is handled through the Vercel AI Gateway, allowing flexible model selection (defaulting to openai/gpt-4.1) and abstracting underlying AI providers. Authentication relies on a single LANGUINE_API_KEY for CLI/Action access, while the dashboard is secured by Vercel's Deployment Protection.

Quick Start & Requirements

• Deployment: One-click deployment to Vercel is available, forking the repository and provisioning necessary services (Postgres, environment variables).
• CLI Usage: Install and run via npx languine@selfhosted <command> (e.g., login, init, translate).
• Prerequisites: Vercel account, GitHub account, LANGUINE_API_KEY (generated randomly), optional AI_MODEL slug.
• Links:
  • Vercel Deployment: (Initiated via "Click Deploy" button)
  • Dashboard: https://<your-deployment>.vercel.app
  • Local Development: git clone, bun install, bun dev.

Highlighted Details

• Full Vercel integration: Next.js 16, Serverless Postgres, Vercel Workflows, Vercel AI Gateway.
• Self-hosted CLI (@selfhosted tag) supports direct project integration and CI/CD pipelines (GitHub Actions example provided).
• Mandatory Vercel Deployment Protection recommended for securing the dashboard and API key.
• Configurable AI models via Vercel AI Gateway (e.g., openai/gpt-4.1, anthropic/claude-sonnet-4).

Maintenance & Community

No specific details regarding maintainers, community channels (Discord/Slack), or roadmap were found in the provided README. Copyright is held by Midday Labs AB.

Licensing & Compatibility

• License: MIT.
• Compatibility: The MIT license permits commercial use and integration into closed-source projects without significant restrictions.

Limitations & Caveats

The backend infrastructure is exclusively hosted on Vercel. Enabling Vercel Deployment Protection is critical to prevent public exposure of the LANGUINE_API_KEY. Local development requires the bun runtime. The @selfhosted CLI tag must be explicitly used to avoid the legacy hosted backend.