Run the entire
AI platform
on your own terms
Deploy ChatBotKit
Your data never leaves your perimeter. You keep the keys. We provide the software.
Network Perimeter
Dashboard
Admin and builder UI
API
Conversation and agent engine
Datasets
Vector store and documents
Model Gateway
Your GPUs or private endpoints
Deployment Models
Three ways
to self-host
Your cloud account, your data center, or a fully air-gapped network - run the platform wherever your policy requires.
Your Cloud Account
Deploy into your own AWS, Azure, or GCP account. The platform runs in your VPC, under your IAM policies, billed through your existing cloud agreement.
A fintech running ChatBotKit in a locked-down AWS account
Private Data Center
Install on your own hardware or private cloud. Full control over networking, storage, and compute, with no dependency on a third-party SaaS.
A bank hosting agents on bare metal inside its own DC
Air-Gapped Network
Run with zero outbound internet access, paired with self-hosted models on your GPUs. Built for classified, defense, and isolated environments.
A defense contractor operating fully offline
Your Platform, Your Control
Every byte
stays yours
From the model that answers to the keys that encrypt, every part of the stack runs under your governance.
Data Stays In Your Perimeter
Conversations, datasets, embeddings, and logs are written to storage you own. Nothing is sent to a third-party SaaS unless you explicitly route it there.
Bring Your Own Models
Connect local open-weight models on your own GPUs, a private inference endpoint, or your organisation gateway. Use commercial providers only when policy allows.
Your Keys, Your Encryption
Hold your own encryption keys and secrets. Integrate with your KMS, HSM, and identity provider so access never depends on credentials we control.
Compliance by Architecture
Data residency, sovereignty, and isolation are properties of where the software runs - not promises in a contract. Simplify HIPAA, GDPR, and FedRAMP reviews.
Full Audit and Observability
Every action is logged inside your environment with complete audit trails. Wire metrics and logs into the monitoring stack your team already runs.
Containerized and Reproducible
Ship as Docker or Kubernetes workloads with infrastructure-as-code. Version-controlled, reproducible deployments across every environment you operate.
Getting Started
From scope to production
in four steps
Scope the architecture, deploy the stack, integrate your systems, and hand over to your operations team.
1.Scope
We map your requirements - cloud or bare metal, model strategy, compliance regime, and network constraints - into a reference architecture.
2.Deploy
Install the containerized stack into your environment with Helm or Compose. Infrastructure-as-code makes the rollout repeatable and reviewable.
3.Integrate
Wire in your identity provider, KMS, models, and monitoring. Connect to internal systems and data sources behind your firewall.
4.Operate
Your team runs the platform with our runbooks, signed releases, and support. Scale, upgrade, and audit entirely within your perimeter.
Use Cases
Built for regulated environments
Healthcare, finance, government, and the public sector - where data cannot leave and compliance is non-negotiable.
Healthcare AI Behind the Firewall
Run clinical assistants and document Q&A over patient records without PHI ever leaving your network. Self-hosted models and full audit trails keep HIPAA reviews simple.
Banking and Financial Services
Deploy agents inside a locked-down account for fraud analysis, internal knowledge, and customer support. Data residency and key control satisfy regulators and auditors.
Government and Defense
Operate fully air-gapped on classified networks. Self-hosted open-weight models on your own GPUs mean no data and no inference ever touches the public internet.
Sovereign AI for the Public Sector
Keep citizen data within national borders. Run the full platform in a domestic cloud or data center to meet data-sovereignty and procurement requirements.
Architecture
Everything runs inside
Users, platform, and models all sit within your perimeter. Traffic never crosses a boundary you do not control.
Your Users
Employees and systems on your network
Your Perimeter
Firewall, IAM, KMS, monitoring
ChatBotKit
Agents, conversations, datasets
Your Models
Local GPUs or private endpoints
The Numbers Behind On-Premise AI
What organisations gain when they run the platform inside their own infrastructure instead of a shared cloud.
of conversations, datasets, and logs stored on infrastructure you own
run inference on your own GPUs or private endpoints, with no third-party dependency
bytes that have to leave your network - air-gapped operation is fully supported
Hosted vs. On-Premise
The same platform on your terms
The hosted platform is fast to start. On-premise gives you control over data, keys, models, and the network they run on.
FAQs
What does on-premise deployment mean for ChatBotKit?
On-premise deployment runs the full ChatBotKit stack inside infrastructure you control - your own cloud account, a private VPC, your data center, or an air-gapped network. The dashboard, API, conversation engine, datasets, and model gateway all run on your hardware, so your data never leaves your perimeter.
Can I run ChatBotKit completely air-gapped?
Yes. ChatBotKit can be deployed with no outbound internet access, paired with self-hosted models running on your own GPUs. Updates and license validation are delivered through an offline channel, so the platform operates fully inside isolated and classified environments.
Which models can I use on-premise?
You can connect any model you control - local open-weight models such as Llama or Mistral running on your GPUs, private cloud endpoints, or your organisation's existing inference gateway. You can also route to commercial providers like Anthropic or OpenAI through your own keys when your policy allows it.
How is ChatBotKit deployed into our infrastructure?
ChatBotKit ships as containers orchestrated with Docker Compose or Kubernetes (Helm). It runs on the major clouds, on bare metal, and inside private data centres. Our team provides reference architectures, infrastructure-as-code, and hands-on support to fit your environment.
Who manages updates, scaling, and maintenance?
Your team owns the runtime, but you are not on your own. We provide signed release artifacts, upgrade runbooks, monitoring dashboards, and a dedicated support channel. Managed and co-managed options are available where our team operates the deployment inside your account under your controls.
How does on-premise help with compliance?
Because data, models, and logs stay inside your boundary, on-premise deployment simplifies meeting requirements such as HIPAA, GDPR data residency, FedRAMP, and internal data-sovereignty policies. You keep full audit trails, encryption keys, and access controls under your own governance.
What is the difference between on-premise and the white-label platform?
White-label lets you resell the hosted ChatBotKit platform under your own brand. On-premise is about where the software runs - inside your own infrastructure for control, sovereignty, and compliance. Many regulated organisations combine both, running a branded platform entirely on their own systems.
How do we get started with an on-premise deployment?
Book a call with our team. We will scope your requirements, recommend a reference architecture, and run a proof of concept in your environment. From there we plan the production rollout, security review, and handover to your operations team.
On-Premise Features
Everything you need to run AI agents inside your own infrastructure. From self-hosted models to full audit trails - all under your control.
Customer Stories
Case studies from teams shipping AI
See how organizations use ChatBotKit to launch production AI assistants, validate new products, support customers, and create richer digital experiences.
Enterprise search
Quench
Discover Quench.ai, the enterprise search company founded by Husayn Kassai, the serial entrepreneur behind Onfido. Quench helps large organizations unify and discover their internal knowledge through natural language search. Built on ChatBotKit's Forward Deployment platform - the environment powering the "Quench Sandbox" - Quench prototypes, runs discovery, and validates AI products with real customers in days rather than quarters. Learn how this approach delivered 10x faster prototyping and won major enterprises including Yum Brands, MotorK, Podium, and numerous Fortune 500 companies, turning rapid customer iteration into a sustainable competitive advantage.
Healthcare charity
Debra
DEBRA UK is the leading charity for individuals with epidermolysis bullosa (EB), a rare genetic skin condition. Committed to providing lifelong care and seeking cures, DEBRA supports nearly 4,000 members across the UK. With over £22 million invested in research, DEBRA is the largest UK funder of EB studies. The organization addresses the complex information needs of patients and caregivers by offering reliable resources and support. Learn about DEBRA's innovative chatbot, providing 24/7 assistance for inquiries about EB, fundraising, and support services, ensuring accurate and compassionate communication. Explore DEBRA's mission to improve lives and advance research for those affected by EB.
Education wellbeing
Elggo
Discover Elggo, the MENA and Southeast Asia region's first AI-powered wellbeing platform for K–12 schools. Founded after the COVID-19 pandemic to close a gap in culturally relevant mental-health resources, Elggo delivers evidence-based curricula designed by regional psychologists and educators. By integrating ChatBotKit's conversational AI, embeddable widget, and multilingual support, Elggo provides students and teachers with always-on, personalized guidance on emotional literacy, decision-making, and growth mindset. Learn how a controlled trial of 12,000 students across 32 schools saw a 30% increase in student wellbeing, and how the platform scaled across seven countries while keeping content culturally responsive and data-driven.
Cultural heritage
Faro
Discover FARO, the Flemish government's cultural heritage organization, which enhances access to heritage collections through its innovative ErfgoedApp. Launched in 2015, the app utilizes augmented reality, IoT, and AI to provide on-site, multilingual guidance for museums and heritage sites. In celebration of its 10th anniversary, FARO has partnered with ChatBotKit to introduce AI chatbots, transforming the app into an on-demand heritage guide. Visitors can ask questions about artworks and historic landmarks at any time, while geofencing technology provides location-aware storytelling. With plans to expand this interactive experience across more sites, FARO is committed to making heritage discovery intuitive and personalized for everyone.
Customer service
Intelliway
Discover Intelliway, a Brazilian technology firm building AI-powered customer service solutions for businesses across Brazil and Latin America. Using ChatBotKit's API-first platform as their backend, Intelliway builds custom-branded interfaces on top of powerful conversational AI while retaining full control over the customer experience. Learn how native Brazilian Portuguese understanding, scalable cloud infrastructure, and advanced language models help Intelliway serve hundreds of clients across multiple industries, with one major retail client reporting a 40% increase in positive customer feedback. Explore how the platform-as-a-backend approach positions Intelliway to lead conversational AI across the Americas.
Ready to run AI inside your own walls?
Book a meeting with our team. We will scope your environment, recommend a reference architecture, and plan a proof of concept in your infrastructure.