HiveChat is an AI chatbot application designed for small to medium-sized teams, enabling centralized management of various AI models for user groups. It supports multiple authentication methods and offers granular control over model access and token limits per user group, streamlining AI tool adoption within organizations.

How It Works

The application is built with a Next.js frontend and utilizes PostgreSQL for data storage, managed via Drizzle ORM. It leverages Auth.js for authentication and Tailwind CSS for styling. The backend architecture supports integration with numerous large language model providers (OpenAI, Claude, Gemini, DeepSeek, etc.) and allows for custom OpenAI-compatible endpoints, providing flexibility in AI model selection.

Quick Start & Requirements

• Local Deployment: Clone the repository, install dependencies (npm install), configure the .env file (PostgreSQL connection, AUTH_SECRET, ADMIN_CODE), initialize the database (npm run initdb), and start the application (npm run dev or npm run start).
• Prerequisites: Node.js, PostgreSQL.
• Vercel Deployment: One-click deployment to Vercel is available, requiring configuration of environment variables, including a Vercel-hosted Neon PostgreSQL database.
• Docker Deployment: Available via docker compose up -d, with a note on potential database schema changes during upgrades.
• Demo: User demo: https://chat.yotuku.cn/, Admin demo: https://hivechat-demo.vercel.app/ (admin credentials: admin@demo.com / helloHivechat).

Highlighted Details

• Supports a wide range of LLM providers including OpenAI, Claude, Gemini, DeepSeek, Moonshot, and more, plus custom OpenAI-compatible services.
• Features administrative controls for user management, group creation, model access per group, and monthly token quotas.
• Offers multiple authentication options: email, WeChat Work, DingTalk, and Lark.
• Includes advanced features like DeepSeek Chain-of-Thought display, LaTeX/Markdown rendering, and image understanding.

Maintenance & Community

• Active development with frequent updates.
• Community contact via WeChat (wuhaoworld) for group discussions.

Licensing & Compatibility

• The repository does not explicitly state a license in the README. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

• Upgrading from older versions may require manual database schema adjustments (e.g., renaming daily_token_limit to monthly_token_limit in the group table for Vercel deployments). Docker upgrades may necessitate data volume resets for database reinitialization.