Private AI support

A self-hosted AI chatbot your customers can actually talk to

Most AI support bots are a black box in someone else's cloud with a per-conversation meter. ZChat's chatbot runs inside your own live chat deployment: point it at a local Ollama model and customer conversations never leave your network, or connect OpenAI or Anthropic with your own keys and pay the provider directly.

Download Free Evaluation See the Product Tour

Local first: Ollama

Point ZChat at an Ollama server and run open models like Llama on your own hardware. No API bills, no data leaving your infrastructure: the strongest possible answer to "where do our customer conversations go?"

Or bring your own provider

Prefer hosted models? Connect OpenAI or Anthropic with your own API keys. You choose the model and pay the provider's rates directly. ZChat adds no markup and no per-resolution fee.

Grounded in your content

The bot answers from your knowledge base: articles you manage in the dashboard, hot-reloaded within seconds of saving. Common answers stay consistent across shifts instead of being improvised.

Human handoff built in

AI answers first. Humans take over the moment it matters.

A support bot is only safe when the exit is obvious. ZChat watches for handoff signals, like a visitor asking for a person or a question beyond the bot's knowledge, and moves the conversation to a live agent. The agent sees the full bot transcript, so the customer never repeats themselves.

1 · First response

The bot greets the visitor and answers routine questions from the knowledge base, streaming replies in real time.

2 · Handoff detection

Configurable keywords and rules trigger escalation. "Talk to a human" always works, and admins tune the rest.

3 · Agent takeover

The session lands in the agent queue with the AI conversation attached; the agent continues in the dashboard or desktop console.

What do I need to run the AI locally?

Install Ollama on a machine ZChat can reach, pull a model, and enter the endpoint and model name in ZChat's chatbot settings. The dashboard lets you tune the system prompt, temperature, and handoff keywords without restarting anything.

Does AI cost anything extra in ZChat?

No. AI support is part of the product on every license. With Ollama your marginal cost is your own hardware; with OpenAI or Anthropic you pay the provider's usage directly. ZChat never meters conversations or resolutions.

Can I turn the bot off, or use it only after hours?

The chatbot is optional and disabled by default. Enable it when it helps, as a first responder in front of the queue or as coverage when no agents are online, and disable it any time from the dashboard.

How do agents benefit from the AI besides handoff?

Agents get AI-suggested replies drawn from the conversation context, which they can edit before sending. Suggestions are permission-checked per session, and the human always decides what goes out.

Why it's different

Hosted AI bots vs ZChat's approach

Model choice is yours: local Ollama, OpenAI, or Anthropic, switchable in settings.

Data path is yours: with local AI, prompts and answers stay on your network.

Cost is flat: no per-conversation or per-resolution pricing from ZChat, ever.

Humans stay in charge: handoff, transcripts, and agent takeover are the default design, not an add-on.

Try It Free on Localhost

Owned customer support software

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

ZChat gives you the installable server, web dashboard, website widget, and desktop agent tools in one self-hosted product you buy once and keep. Run it on infrastructure you trust and connect AI only if and how you want it.

Download ZChat 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

One-time purchase, perpetual license, and no monthly per-agent bill attached to growth.

AI Flexibility

Use Ollama locally or connect OpenAI and Anthropic with your own provider accounts.