sdcb/chats

A powerful and flexible frontend & AI gateway for large language models, supporting 21+ mainstream AI model providers.

What it solves

Sdcb Chats provides a unified, flexible frontend for interacting with over 22 different AI model providers. It eliminates the need to manage multiple separate interfaces by consolidating various LLM APIs into a single entry point with enterprise-grade management features.

How it works

Built with C# and TypeScript, the project acts as both a user interface and an API gateway. It supports standard protocols (Chat Completions, Messages, Responses, Gemini) and can be deployed quickly via Docker or as a native executable. It includes a Docker sandbox for a code interpreter (supporting browser, code execution, and Excel tools) and offers flexible storage options including SQLite, SQL Server, PostgreSQL, and various cloud storage providers (AWS S3, Aliyun OSS, Azure Blob).

Who it’s for

It is designed for individuals and enterprises who want a centralized hub to manage multiple AI models, as well as those needing a secure, multi-user environment with permission controls, balance management, and SSO integration.

Highlights

  • Broad Compatibility: Supports 22+ mainstream AI model providers.
  • Integrated Tooling: Features a code interpreter with a Docker sandbox for executing code and handling files.
  • Enterprise Security: Includes user permission management, account balance controls, rate limiting, audit logs, and Keycloak SSO.
  • Observability: Provides full-link Request Trace to debug inbound and outbound requests.
  • Multimodal Support: Capable of handling vision inputs and image generation.

Related

  • Project
    fruitbars/simple-one-api

    A unified API gateway that connects multiple LLM providers and provides a single interface compatible with OpenAI and Anthropic protocols.

  • Project
    haydenbleasel/files-sdk

    A unified storage SDK that provides a single API for interacting with multiple object and blob backends like S3, GCS, and Azure.

  • Project
    danny-avila/LibreChat

    A self-hosted AI chat platform that unifies all major AI providers into a single, privacy-focused interface with support for agents, code execution, and multi-user management.

  • Project
    theopenco/llmgateway

    An open-source API gateway that acts as middleware between applications and multiple LLM providers to unify API interfaces and track usage costs.

  • Project
    johnson7788/MultiUserClaw

    MultiUserClaw is a Docker‑based SaaS framework that lets you run isolated AI assistants (Hermes agents) for many users. It includes a React front‑end, a FastAPI gateway for auth, container management and LLM proxying, per‑user Hermes containers, PostgreSQL storage, and features like knowledge bases, skill store, cron jobs, multi‑channel bots, and multi‑model support.