<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> DeepV Code Server (deepx-mini-server) is a lightweight AI proxy server designed to unify access to multiple Large Language Model (LLM) providers, including Google Vertex AI and OpenRouter. It offers a standardized API interface for the DeepV Code Client ecosystem, simplifying integration and accelerating development by abstracting away provider-specific complexities.

How It Works

Built with Node.js and TypeScript, this server acts as an intermediary, forwarding requests to various LLM backends. It provides a unified chat interface supporting both streaming and non-streaming responses, automatically converting diverse provider outputs into a consistent Google AI format. This approach streamlines client development by offering a single, predictable API endpoint, regardless of the underlying LLM service. A built-in mock JWT login interface facilitates development and testing.

Quick Start & Requirements

• Installation: npm install
• Prerequisites: Node.js v18+ recommended, npm or yarn.
• Configuration: Requires a .env file with OPENROUTER_API_KEY and VERTEX_CREDENTIALS_PATHS.
• Running: npm run dev for development; production deployment via PM2, Docker, or Systemd is recommended.
• Docs: README serves as primary documentation.

Highlighted Details

• Supports Google Vertex AI and OpenRouter.
• Provides a unified chat API with streaming and non-streaming capabilities.
• Automates response format conversion to a standardized Google AI structure.
• Includes a mock JWT login endpoint for development convenience.
• Offers enterprise-grade API key solutions through Google Cloud Certified Partners.

Maintenance & Community

The project welcomes forks and pull requests. Specific community channels (e.g., Discord, Slack) or a roadmap are not detailed in the README. The project is associated with Google Cloud Certified Partners.

Licensing & Compatibility

• License: Apache 2.0.
• Compatibility: Permissive license suitable for commercial use and integration into closed-source applications.

Limitations & Caveats

The project includes mock authentication and hardcoded test data in the login interface, requiring anonymization for production use. Security best practices emphasize avoiding committing environment variables and credential files to version control. Debug logs may contain sensitive data and should be handled carefully.