Data ownership

Where is your live chat data stored?

Every live chat conversation is a record of a customer relationship - and someone decides where it lives. With hosted tools, that's the vendor's cloud. With a self-hosted product, it's your own database. Here's what gets stored, who can reach it, and how to keep it under your control.

Keep Your Data - Try Free GDPR-Compliant Live Chat

Hosted: the vendor's cloud

SaaS live chat stores transcripts and visitor records on the vendor's servers. Where they sit geographically, how long they're kept, who at the vendor can access them, and how they're used to train models are all set by the vendor's policies, not yours.

Self-hosted: your database

DChat stores everything in your own SQL Server: transcripts, visitor details, department and agent assignment, CSAT ratings, and an audit log. It sits on infrastructure you control, backed up and secured with the tools you already use - including support email, which lands in the same database.

The AI question

AI features can quietly send conversations to a model provider. DChat's chatbot can run on a local Ollama model so nothing leaves your network, or use your own OpenAI/Anthropic keys - either way, you decide what is sent and to whom.

What a live chat actually stores

In DChat, every one of these lives in your own SQL Server database.

Data	What it is	In DChat
Transcripts	The full message history of each conversation	Your database
Visitor records	Name, email, the page and referrer, IP	Your database
Ratings & feedback	CSAT scores and post-chat comments	Your database
Audit log	A record of admin and operator actions	Your database
Attachments	Files shared in a conversation	Your server
AI prompts	What the chatbot processes to answer	Local with Ollama, or your provider

Control you can prove

Own the data, and the tools to manage it

Because the data is in your database, you set retention, you run the backups, and you answer a data-subject request without filing a ticket with a vendor. DChat ships GDPR export and erase-by-email plus an audit log, so honoring privacy requests is a built-in action rather than a support conversation. For healthcare teams, see live chat for HIPAA environments. For the specifics of how the data is defended in transit and at rest, see what DChat actually does about security.

Built in

GDPR export and erase/anonymize by email, audit log of admin actions, IP blocking, and direct SQL access for your own retention rules.

Optional, local

Run the AI chatbot on a local Ollama model so conversations are never sent to a third-party model provider.

Where does live chat software store conversations?

With hosted (SaaS) live chat, conversations are stored in the vendor's cloud, subject to their retention, access, and data-location policies. With self-hosted live chat like DChat, conversations are stored in your own database on infrastructure you control.

What live chat data is stored?

Typically message transcripts, visitor details (name, email, the page they were on), department and agent assignment, CSAT ratings, and an audit trail of admin actions. In DChat all of it lives in your own SQL Server database.

Can I delete a visitor's chat data on request?

Yes. DChat has built-in GDPR tools to export a visitor's records and to erase or anonymize them by email, and it logs the action in the audit trail. Because the data is in your database, you can also apply your own retention policies directly.

Does the AI chatbot send my conversations to a third party?

Only if you choose a hosted model. Point DChat's chatbot at a local Ollama model and the AI runs entirely on your own server with no data leaving your network. If you prefer OpenAI or Anthropic, you connect your own keys and control what is sent.

Self-hosted customer support software

Deploy live chat on your own terms, not on someone else's pricing model.

DChat gives you the installable server, web dashboard, website widget, and desktop agent tools in one self-hosted product, with live chat free to run, and an AI agent that answers, acts with the approvals you set and hands off to your team when you want one. Run it on infrastructure you trust, on the model you choose.

Download DChat See Product Demo

Deployment

Install on Windows or Linux, behind IIS or Nginx, in a VM, or in Docker if that fits your stack.

Commercial model

Live chat is free with unlimited agents. Premium, with the AI agent, is billed per agent per month, never per conversation.

AI Flexibility

Run the AI agent on a local Ollama model, or connect OpenAI and Anthropic with your own provider accounts.