ON-PREMISE ARCHITECTURE

Self-Hosted Chatbot On Your Own Servers

Eliminate cloud dependencies and recurring SaaS message fees. Host your chatbot directly within your existing web environment with complete data sovereignty and SQLite indexing.

Explore On-Premise Engine Infrastructure Specs

On-Premise Engine

Isolated Host
All processing runs locally on your server. Zero external data exposure.
my chat assistant

On-Premise Architectural Capabilities

Maximum performance with zero third-party API dependencies.

100% Local SQLite Storage

Store all conversation logs and search indices inside an isolated local SQLite file on your web host.

Bring Your Own Model Keys

Connect Anthropic, Google Gemini, or any OpenAI-compatible endpoint using your own API key. The free BM25 retrieval engine works without one; the optional RAG layer only composes answers from content already retrieved from your site, never from the model's general knowledge.

Zero SaaS Message Subscriptions

Say goodbye to monthly tier caps and per-message charges. Pay strictly for your standard host server resources.

Built for UK Data Handling

Conversation data stays on your own server rather than a third-party host, with configurable log retention, supporting your UK GDPR obligations without extra plugins.

Air gap iconAir Gap by Default

No AI provider key is connected out of the box. Until you deliberately connect one of your own, any point where a question would otherwise go to an AI model hands you a composed prompt to copy and paste into a model of your choosing yourself. My Chat Assistant makes no network call to any AI model on your behalf unless you've connected one.

Diagram comparing on-premise deployment with a typical hosted chatbot SaaS: your knowledge base, conversation logs, and retrieval engine all stay inside your own infrastructure on the left, versus a vendor's cloud holding your uploaded content, logs, and retrieval logic on the right.

On-premise vs. a typical hosted chatbot — what stays inside your own infrastructure.