Put your organisation’s knowledge to work.

Give employees AI for the documents, questions and workflows that matter to your business. Aventail^™ Enterprise brings model deployment and execution, policy-based routing, central management and Aventail^™ Workspace together, so your teams can use approved models while you control where work runs.

See the team experience

Aventail™ Workspace interface showing conversations, documents and team workflows — Aventail^™ Workspace — conversations, documents and workflows

Security

View trust centre

AI for the work your teams already do.

In Aventail^™ Workspace, employees search and process documents, ask questions and get answers with references to their sources. Role-based access control sets who can use what, and saved history lets people return to earlier work.

Teams that already use supported apps such as Claude Desktop, Claude Code and OpenCode can bring their model requests under the same rules through Aventail^™ Connect. Run supported models on your own infrastructure, decide when approved external providers may be used and keep the costs of each choice visible.

Aventail^™ Link combines an LLM gateway and inference engine, connecting your applications to supported models on your hardware and approved external APIs. Routing policies are applied locally on each machine.

Deploy a private AI workspace across laptops and servers

Set the boundary.
Choose the compute.

Keep sensitive work on approved infrastructure, use existing capacity for suitable requests and allow frontier APIs when the work needs them.

Team requestSensitive team request

On this machineAventail^™ Link local policy

Execution destinationOn-premises machine

Illustrative policy example

Sensitive work

A permitted model runs on an on-premises machine equipped with Aventail^™ Link. The policy keeps this request within approved infrastructure.

Contract review on an internal server

Illustrative workflow: a team asks a supported model to summarise a confidential contract on an approved internal server running Aventail^™ Link. The device policy selects that server as its network-peer primary, with the exact model available and Serve other devices enabled. No external provider or fallback is configured; if the server is unavailable, the request fails. Aventail^™ Control distributes the policy and stays outside the inference request path. Review document storage and access separately from inference routing.

An employee reviews the summary against the source document; the pilot assesses output quality, reviewer effort, cost and reliability.

Peer routing is available in beta.

Plan a laptop and server deployment

Verify the data boundary

Put AI to work on information that cannot leave your environment.

Search internal documents, summarise sensitive material and answer operational questions using supported models on infrastructure your organisation approves.

Connected private

Run supported models on your infrastructure and use approved external AI providers where policy permits.

Restricted connectivity

Limit network access to approved destinations and apply your routing policies to model requests.

Fully disconnected

Aventail^™ Link runs installed, supported models locally. For disconnected enterprise deployments, Aventail^™ Control can also run inside your environment.

Approved destinations and fallback paths are constrained by policy. If no destination is permitted, the request fails.

Validate installation, dependencies, licensing, identity, storage, updates and the complete application workflow for your environment. Aventail^™ Connect governs model requests, not every network connection an app makes.

Plan an air-gapped AI deployment

Keep sensitive work within your boundaries

Set which models and destinations each workflow may use. Apply the same data boundaries to fallback paths.

Control when you pay for external AI

Use your devices and servers for suitable work, and set when paid APIs are allowed. Local execution still has hardware, energy and platform costs.

Manage machines and policy together

Use Aventail^™ Control to distribute models, policies and keys, then review device and routing activity across machines running Aventail^™ Link.

Roll out your AI tools. Keep one set of rules.

Aventail^™ Connect is available for enterprise deployment through our fleet management tooling. Roll it out across employees’ machines so supported model requests from Claude Desktop, Claude Code and OpenCode follow your organisation’s routing policies. Manage policies centrally through Aventail^™ Control, with the LLM gateway in Aventail^™ Link applying them on each machine.

Set up Claude Desktop and Claude Code with Aventail^™ Connect

Review the Claude Code security checklist

Read the guide to reducing AI provider dependency

Route requests between local models and approved cloud APIs

Aventail™ Control interface showing machines, models and routing policy management — Aventail^™ Control — routing rules and fallback order

See the rules. Keep prompts out of hosted Aventail^™ Control.

Aventail^™ Control lets you manage routing rules and fallback order, with configuration distributed ahead of requests.

The hosted Aventail^™ Control service receives device and routing events, not prompts or responses. An approved external provider processes the request through your organisation’s own account. Aventail^™ Control can also be hosted on your infrastructure.

Comparing a single-machine tool with managed team deployment? Compare Aventail^™ with LM Studio

Questions from IT, security and AI teams.

What data leaves our machines?

Local execution keeps inference on the machine. A policy-permitted remote destination receives the request sent to it. Hosted Aventail^™ Control receives management, device and routing events, not prompt or response bodies. Local execution alone does not determine application storage, analytics or plugin behaviour; review those settings. Read the architecture and usage analytics guidance.

Where can our AI requests run?

On an eligible local device, another approved reachable peer running Aventail^™ Link, or on-premises, private-cloud or provider machines running Aventail^™ Link. Approved frontier APIs run at their providers, using your own provider accounts. Model support, connectivity, access and your policy determine which destinations are eligible.

Can routing use model and device performance?

Yes. Integration with the inference engine lets Aventail^™ Link combine model suitability and performance with device capacity and conditions, query content and organisation policy in a local decision. Constraints restrict eligible destinations before preferences select among them.

Can we deploy with restricted connectivity or fully disconnected?

Yes. Aventail^™ Link runs installed, supported models without connectivity, and enterprise Aventail^™ Control can run locally. Full-application isolation still requires validation for your environment. Review the deployment options.

Which models and hardware are supported?

Support depends on the runtime version, operating system and architecture, model engine and format, and available resources. Current documentation lists Mac Apple Silicon, Linux x64 and Windows x64 packages; package availability does not mean every model or machine is supported. Read the compatibility guide.

Where are routing policies applied?

Aventail^™ Control configures and distributes policies. Aventail^™ Link evaluates requests locally and applies restrictions to destinations and fallback paths. Aventail^™ Control stays outside the inference request path. Read how Aventail^™ works.

Can we use our own models alongside frontier APIs?

Yes. Run supported open-weight models on your own compute and permit external calls through your own provider accounts. The same policy layer governs those choices without requiring an all-cloud or all-local deployment.

What can our security team review?

Review the security and trust overview, including SOC 2 Type II, the DPA, the Privacy Policy and the security documentation alongside your deployment requirements.

Is Aventail^™ Link open source?

Aventail^™ Link is not currently open source. We intend to open-source it by the end of 2026 and are evaluating the appropriate licence and release approach. Link 1.0 was open source, and we want to bring the current generation to the community too. We will share the scope, licence and contribution process when they are confirmed. Read our open-source plans.

Start with one useful workflow.

Bring one employee workflow, the data it uses and the hardware or model services you already have. We’ll agree the approved data and deployment for a pilot, then assess output quality, reviewer effort, cost and reliability with you.

Choose a time with our team.