Aventail™ lets your teams use AI while you control which models process their requests and where that processing happens. Keep sensitive work on approved infrastructure, and use external AI providers where your policies allow.
With a built-in inference engine and routing rules evaluated on your machines, Aventail™ brings model deployment, execution and control into one platform.
Control which models may process a request, which destinations may receive it and where processing may happen. Set allowed fallback paths so sensitive work stays within the boundaries your organisation approves.
Give teams an approved way to use AI through Workspace and supported Aventail™ Connect apps, with model requests governed by your routing rules.
These controls apply to requests routed through Aventail™. They do not discover or block tools used outside it.
Apply your organisation’s requirements first, then use model capabilities, query context and device conditions to choose among supported, approved models and destinations based on task fit and compute availability.
Use suitable compute you already operate, and call paid external APIs when your policy permits.
Begin with one workflow on your own infrastructure. Expand to other devices, private-cloud machines and approved providers as your requirements grow. Read the guide to keeping sensitive requests within approved infrastructure.
Get the desktop app, or install the runtime from your terminal.
Free for personal and business use.
View plans and limitsSecure on-device content-aware routing. Aventail™ Link evaluates query context, model fit and device conditions locally, applying your organisation’s requirements before selecting an approved execution destination.
Interactive illustration. Example signals and infrastructure; no query is sent.
Summarise this fictional confidential employee case for our internal review.
Aventail™ Link will evaluate the query and constraints locally. No query leaves this illustration.
Example properties only. Default order: this device, another machine, on-premises server, private-cloud machine, provider server, frontier API. Lower-latency preference order: this device, another machine, frontier API, provider server, private-cloud machine, on-premises server. Approval is configured by the organisation, not a certification; latency ordering is illustrative, not measured. Hard requirements always win.
UK · Organisation-managed · Standard model · Not on example ESG-approved list
UK · Organisation-managed · Standard model · On example ESG-approved list
UK · Organisation-managed · Standard + advanced model · Not on example ESG-approved list
Outside UK · Organisation-managed · Standard + advanced model · On example ESG-approved list
UK · External provider · Standard + advanced model · On example ESG-approved list
Outside UK · External provider · Standard + advanced model · Not on example ESG-approved list
Content analysis and policy checking happen inside Aventail™ Link. Aventail™ doesn’t need the query to make the routing decision.
Aventail™ Control distributes configuration ahead of time. Prompts and responses do not pass through the hosted Aventail™ Control service. Approved destinations receive the requests routed to them; frontier API calls use your own provider account. See how Aventail™ Link Server works for inference providers.
Aventail™ brings model deployment, execution, routing and management into one system. Aventail™ Link combines an LLM gateway and inference engine on your machines. Aventail™ Control manages them. Aventail™ Connect brings supported apps under your routing rules. Aventail™ Workspace gives your teams a place to use AI.
Manage machines, models and routing policies centrally. Distribute configuration to Aventail™ Link and review device and routing activity, outside the inference request path.
Workspace and supported AI on your devices. Free for personal and business use, with more capacity and email support when you need it.
A real plan for personal and business use. Start with Workspace and supported models running on your devices.
Start freeFree forever, including business use. This is not a Starter trial.
More connected devices, model registry storage and transfer allowance, with email support.
Start 30-day free trial30-day free trial. Returns to Free when the trial ends.
Additional usage is charged separately at the rates below. Overage is billed monthly in arrears.
Starter additional usage is billed monthly in arrears. All paid prices exclude VAT.
| Resource | Included | Additional usage, excluding VAT |
|---|---|---|
| Connected devices | 10 devices | £5 per device per month |
| Model registry storage | 50 GB | £0.05 per GB per month |
| Outbound data transfer | 100 GB per month | £0.14 per GB |
Aventail™, formerly Locai, was founded in May 2025 and is a graduate of Google AI First.
Saif Al-Ibadi and Joseph Ward have built production AI together since 2018, from neuromorphic computing to generative design for aerospace.
That experience shaped Aventail™: AI has to work with the hardware, connectivity and constraints in front of it.
Aventail™ Link includes an LLM gateway and a built-in inference engine. It can deploy and execute supported models on your hardware, or route requests to another approved machine running Aventail™ Link or an external AI API. Content and policy are evaluated locally. Aventail™ Control manages machines, models and policies outside the inference request path.
Yes. Aventail™ Link runs on your devices and servers, and Aventail™ Control may be hosted by Aventail™ or in your own estate.
The hosted Aventail™ Control service receives device and routing events, not prompts or responses. Aventail™ Link evaluates the applicable local policy on your machine.
Yes. Policy can route to a model on this device, another machine running Aventail™ Link or a frontier API through your own provider account. Local execution can continue offline when the required model is installed and your policy allows it. Remote machines and APIs require a connection.
The request fails with an error. It is not sent to a disallowed destination. Review your policy and the availability of approved destinations.
Yes. Free is free forever for personal and business use, within its included allowances. It is a permanent plan, not a Starter trial.
Starter includes more connected devices, model registry storage and monthly outbound data transfer, plus email support. Additional usage is charged at the rates in the pricing section, excluding VAT, and billed monthly in arrears.
Local storage on your own devices is unlimited on both plans, subject to the storage available on your hardware. Model registry storage and monthly outbound data transfer have separate included allowances.
Start with one useful workflow. Book a conversation with our team to discuss its requirements, your existing systems and the constraints that matter.
Bring one AI use case and the data boundaries that matter. We’ll discuss the models, approved infrastructure and routing rules your first deployment needs.
