Skip to content
>sdcb.ai

Every LLM,one gateway

Sdcb Chats is a powerful, flexible LLM front-end and AI gateway written in C# and TypeScript — self-hosted, your data stays yours.

202.8k Docker pulls22+ providers18 1.x releases
Sdcb Chats
Sdcb Chats screenshot
Azure AI FoundryOpenAIAnthropicGoogle AIDeepSeekMoonshotAlibaba BailianTencent HunyuanBaidu QianfanZhipu AIiFlytek Spark01.AIMiniMaxVolcengine ArkSiliconFlowOpenRouterOllamax.aiGitHub ModelsXiaomi MiMoNovita AI小马算力Azure AI FoundryOpenAIAnthropicGoogle AIDeepSeekMoonshotAlibaba BailianTencent HunyuanBaidu QianfanZhipu AIiFlytek Spark01.AIMiniMaxVolcengine ArkSiliconFlowOpenRouterOllamax.aiGitHub ModelsXiaomi MiMoNovita AI小马算力

Chats 2.0

From a chat app to an agent platform that gets work done

2.0 is about agents: a persistent place for the AI to work, a way to publish what it builds, and collaboration that feels like working with a reliable colleague.

Persistent Docker workspaces

Containers outlive a single chat — the environment you set up last time is still there next time.

  • Long-lived containers alongside today’s per-session ones
  • Dedicated volumes, so databases don’t live inside the container
  • Per-chat choice of which containers the AI may see
  • Quotas on CPU, memory, network and container count; admins unlimited
  • One console: users see theirs, admins see everyone’s

Ship a website from the chat

Tell the AI “make it public on this subdomain” — and it’s live.

  • Containers serve the site; traffic enters through the gateway
  • Caddy 2 gateway and port mapping configured over its API
  • Pluggable DNS, starting with Alibaba Cloud DNS and Cloudflare

An agent that asks — and listens

It asks when things are unclear, and you can chime in mid-run.

  • Ask Question: several clarifying questions at once; the ReAct loop resumes on answer
  • Plan / clarify mode must ask about unknowns; normal mode aims to finish in one go
  • Steering: no need to stop — your note is injected after the next tool call

Stateful files & images

Upload an image once; later turns reference the provider’s file ID.

  • Uploads go to our own storage and to providers that support file IDs
  • No more re-sending Base64 or URLs — much faster multi-turn image chats
  • Across Responses, Anthropic Messages and Chat Completions, with expiry handled

Streams that survive a refresh

Reload the page and the AI is still visibly at work — and still stoppable.

  • SSE progress persisted to the database and replayed on reload
  • Stop tokens persisted too, so Stop works after a refresh
  • Cleaned up periodically once a turn completes

Watching: subagents. Interesting, but speed and control come first — not part of 2.0.

Directions, not commitments — scope and timing may change.

Available today

Why Sdcb Chats

One entry point

22+ model providers behind a single entry point.

Up in minutes

One-line Docker deploy, native executables for 8 platforms.

Code interpreter

Docker sandbox with browser, code execution, Excel and more.

API gateway

Chat Completions / Messages compatible — plug in Claude Code directly.

Standard protocols

Chat Completions, Messages, Responses, Gemini — with interleaved thinking.

Observability

Request Trace follows every inbound and outbound call end to end.

Multimodal

Vision input and image generation.

Flexible storage

SQLite / SQL Server / PostgreSQL; local, S3, OSS or Azure Blob.

Enterprise-ready

Permissions, balances, rate limits and audit logs; Keycloak SSO and SMS login.

Quick start

One command to run it

Requires Docker. Then open http://localhost:8080 and sign in with chats / RESET!!!.

Native executables for 8 platforms across Windows / Linux / macOS are also available.Downloads

bash
mkdir -p ./AppData && chmod 755 ./AppData && docker run --restart unless-stopped --name sdcb-chats \
  -e DBType=sqlite -e ConnectionStrings__ChatsDB="Data Source=./AppData/chats.db" \
  -v ./AppData:/app/AppData -v /var/run/docker.sock:/var/run/docker.sock \
  --user 0:0 -p 8080:8080 sdcb/chats:latest