DEEIX-AI/DEEIX-Chat

An enterprise AI workspace for model routing, multimodal chat, files, tools, billing, identity, and operations.

What it solves

DEEIX Chat is an integrated AI platform designed for individuals, teams, and enterprises to maintain stable, unified access to multiple AI model providers. It eliminates the complexity of managing multiple separate API keys and provider interfaces by providing a single entry point for multimodal chat, model routing, and operational management.

How it works

The platform uses a Go-based backend that acts as an orchestration layer between the user and various AI providers (such as OpenAI, Anthropic, Google, and xAI). It handles protocol adaptation, model routing (including priority and weights), and identity management. The frontend is a Next.js application that provides the chat interface and an admin console. For advanced data handling, it integrates with vector databases (pgvector or sqlite-vec) for RAG and optional external services for OCR and document extraction.

Who it’s for

  • Enterprises needing centralized control over AI model usage, billing, and audit logs.
  • Teams requiring a shared AI workspace with integrated file retrieval and tool use.
  • Individuals looking for a professional-grade, self-hosted AI chat interface with multi-provider support.

Highlights

  • Enterprise-Grade Management: Includes usage billing, subscriptions, identity management (SSO/OIDC), and detailed audit logs.
  • Model Routing: Advanced routing capabilities including circuit breaking, vendor mapping, and weight-based distribution.
  • RAG & File Handling: Built-in support for file uploads, OCR, semantic retrieval, and full-context injection.
  • Tool Ecosystem: Integration with MCP (Model Context Protocol) servers and provider-native tools.
  • Flexible Deployment: Supports lightweight SQLite setups for personal use or scalable PostgreSQL/Redis stacks for production.

Related

  • Project
    epam/ai-dial-chat

    AI DIAL Chat is a full‑stack, Nx‑based chat platform (React 19 front‑end + NestJS API) that integrates with EPAM’s AI DIAL Core. It offers modular UI libraries, multi‑provider authentication, overlay iframe embedding, theming, and i18n, with scripts for building, testing, and publishing.

  • Project
    onyx-dot-app/onyx-foss

    Onyx is a self-hosted knowledge and context layer that connects to over 50 applications to provide AI agents with secure, relevant access to your organization's internal data.

  • Project
    Shy2593666979/AgentChat

    AgentChat is an open‑source, full‑stack conversational AI platform. It combines a Vue 3 front‑end with a FastAPI + LangChain back‑end to deliver LLM‑driven chat, multi‑agent collaboration, three‑tier memory (short‑term, summarised history, long‑term user prefs), RAG via vector stores, tool calling (including custom OpenAPI tools), and Model‑Context‑Protocol integration. Docker‑compose provides one‑click deployment; the project is MIT‑licensed.

  • Project
    vual/lobe-chat-pro

    Lobe Chat Pro is an open‑source, self‑hosted AI chat platform (fork of lobe‑chat) that adds a full admin console, user/group management, multi‑vendor model pricing, payment integration (WeChat, Stripe, etc.), and multimodal “infinite canvas” panels for image, music, and video generation. Deployable via Docker in three flavors: full back‑office, gateway‑only with login, or gateway‑only without login.

  • Project
    ThinkInAIXYZ/deepchat

    DeepChat is an open-source, local-first desktop client that unifies AI models, agent protocols like MCP and ACP, and reusable skills into a single, traceable workspace.