# DEEIX-AI/DEEIX-Chat

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

Repository: https://github.com/DEEIX-AI/DEEIX-Chat
Canonical: https://ross.abutalabs.com/products/deeix-chat
Homepage: https://deeix.com
Language: Go
License: Apache-2.0
License Family: permissive
Topics: ai, ai-chatbots, llm, mcp, open-source, rag, self-hosted, ui, webchat, webui
Last push: 2026-08-26T09:18:45+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 98, longevity 7
- inputs: {"age_days": 104, "days_push": 7, "days_rel": 13, "gap_med": 3.5, "n_releases_24m": 19}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1352, forks 200 (observed 2026-08-28T04:04:28.460263+00:00)

## What it is
DEEIX Chat is an open-source, self-hostable enterprise AI workspace that unifies access to multiple LLM providers behind one entry point, with multimodal chat, model routing, files and RAG, MCP tools, billing, identity, and operational controls. It is built with a Next.js frontend and a Go backend and is designed for lightweight, reliable deployment for individuals, teams, and enterprises.

## Use cases
- self-host a multi-user chatgpt-style workspace for my team
- route requests across OpenAI, Anthropic, Gemini and other providers from one endpoint
- chat with my uploaded documents using RAG and embeddings
- connect MCP tools to an internal AI assistant
- manage model access, quotas, and usage billing for an organization
- add SSO and audit logging to an internal LLM deployment
- process and OCR uploaded files into conversation context

## When to choose
- you need one self-hosted gateway and UI for multiple LLM providers
- you want built-in RAG, file processing, and MCP tool support without assembling separate services
- you need enterprise features like billing, identity, 2FA/SSO, and audit logs
- you want a lightweight Go/Next.js stack with low runtime footprint

## When to avoid
- you only need a simple single-provider chat UI with no admin or routing needs
- you want a mature product with a long track record and large community
- you need deep customization of the frontend beyond what the product exposes
- you require provider features not covered by its OpenAI/Anthropic/Gemini/xAI/OpenRouter adapters

## Facets
- artifact type: application
- maturity: active
- function: chatbot, rag, mcp, llm-inference, api-gateway, search-engine, ocr, file-upload, auth
- domain: large-language-models, chatbots, self-hosted, web-development
- platform: self-hosted, go
- tags: model-routing, multi-provider, chat-ui, enterprise-ai, nextjs, pgvector, usage-billing, sso, billing, retrieval-augmented-generation, ai-agents, web-server, docker, nodejs

## Member repositories
- DEEIX-AI/DEEIX-Chat (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:28.460263+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:42:07.659083+00:00, confidence not recorded.
  - readme: https://github.com/DEEIX-AI/DEEIX-Chat (fetched 2026-08-28T04:04:28.460263+00:00, sha 35da12121d4e)
  - homepage: https://deeix.com (fetched 2026-08-29T12:00:35.537505+00:00, sha 515bffe3fe76)
  - site_page: https://deeix.com/docs/deeix-chat (fetched 2026-08-29T12:00:35.547109+00:00, sha 1a2a91c9a135)
- Data as of 2026-08-30T08:39:29.467469+00:00.