Skip to content

FAQ

Short, honest answers to the questions newcomers ask most. Every capability claim below carries a status badge. The single source of truth for status is the Roadmap & status table. For the safety model behind these answers see How GaugeDesk protects your work, and for the words used here see the glossary.

The one truth to read first

GaugeDesk orchestrates locally, but inference is remote. The workbench runs on your machine. The agent uses the third-party LLM provider you configure, so your prompts and the in-scope context are sent to that provider over the network. There is no local-only inference today. Available See Where your data goes.

Data, providers & trust

Does my data stay on my machine?

Your project, resources, and the append-only history are stored locally. Available

Sharing with another party — federation — is opt-in, but it is not operationally available end-to-end today: it is implemented and exercised only in a loopback + NAT-isolated CI harness, not as a shippable cross-machine path. Built

But the agent's reasoning runs at the third-party LLM provider you configure — so your prompts and the in-scope context are sent to that provider over the network. There is no local-only inference today. Available See Where your data goes.

Which LLM providers can I use?

You configure your own provider (for example, OpenAI, Anthropic, Azure OpenAI) and sign in to / supply credentials for it. Available

With your own credentials, the LLM relationship is yours — the provider is your subprocessor, not GaugeWright's. Its retention and training terms are the provider's. If your data may not leave for a third-party model, use a provider you have contracted, or wait for confidential inference (removing the provider from the trust boundary), which is on the roadmap. Planned

Who can see my plaintext?

Stated plainly:

  • You can, on your own machine. Available
  • The LLM provider you configure can — prompts and in-scope context are sent to it for inference. Available
  • A relay cannot. A relay is the transport role in federation — it queues, retries, and forwards encrypted bridge messages between machines, but is never a payload authority and gains no payload access from carrying a handle. When you collaborate across machines, the relay routes only encrypted bytes and never reads payload (this is a machine-checked invariant, INV-14, not a policy promise). Cross-machine federation itself is Built (CI harness only), so this protection holds by construction but is not yet a shippable end-to-end path.
  • GaugeWright (the company) cannot: there is no hosted service holding your data today. (Cross-machine federation is not operationally available, see below.) Available

See the full data-flow treatment in How GaugeDesk protects your work.

Pricing

What is free, and what is paid?

The current pricing direction separates free/open-source capability from paid managed operation and paid enterprise governance:

Use Price
Local, single-party workbench (build · run · review) Free / open-source target Available
Core protections (handles, admission, review/release, export, audit structure) Free / open-source target
Self-operated federation (your own machines or your own relay) Free / open-source target Built (productized operation still limited)
Account ledger / blind directory (pubkeys, device registry, routing pointers, sealed account blob) Free managed exception Planned
Enterprise governance (SSO, SCIM, RBAC, audit, admin controls, security policy, governed thin-client workspace) Paid enterprise / source-available target Built live Planned
Managed cloud services (tokens, VMs, hosted workspaces, hosted relay, public embed host, KMS/SKR, attestation issuer) Paid managed service Planned
Attested sealed runs (confidential VM, metered compute floor) Commercially metered verifier Built live Planned

Self-federation and Relayed multi-party

Federation the mechanism is free/open: the protocol, lifecycle, and self-operated path must remain inspectable and usable without a paid GaugeWright service. GaugeWright-operated federation is different: when our hosted relay, broker, or workspace carries a crossing between separate parties, that is a paid managed service. Relays still do not read payloads. Metering bills operation, not content.

The paid model has three parts:

  1. Enterprise governance entitlement: SSO, SCIM, RBAC, audit, admin controls, security policy, and governed thin-client workspace capabilities are paid enterprise features, with source available under commercial terms.
  2. Managed cloud usage: tokens, VMs, hosted workspaces, hosted relay, KMS/SKR, hosted embed sessions, and attestation infrastructure are paid because they consume cloud resources or create platform obligations.
  3. Settlement / metering: experts set their own engagement price, and GaugeWright can take a rail-contingent application fee when billing runs through the settlement plane. Attested runs also carry a metered compute floor (cost + margin) that is billed to the expert/consultant by default.

Billing is policy layered over the system's safety machinery. It is never run or access authority — paying for something does not by itself grant the right to deploy or run it. The Stripe settlement rails have been verified in test mode, but production go-live, hosted infrastructure, enterprise packaging, and commercial licensing are still Planned. See the roadmap.

Today

Only the local single-party workbench is shippable and free today. The repo is not open source yet (license = "UNLICENSED"), enterprise governance is built but not operationally live, and the paid managed services are not live production products yet.

Deploying agents

Can I deploy an agent to a client today?

Not operationally yet. Cross-party packaging and deployment are implemented and tested in the core, but live deployment to a remote client is not yet wired up. Built live Planned

What you can do today:

  1. Build an archetype on the local workbench and refine it in an edit chat. Available
  2. Run and review it locally — each run works in an isolated sandbox and returns a diff you keep or discard. Available

What is Built but not yet operationally available to end-users:

  • Collaborate across machines with another party through federation (certificate-pinned TLS, a relay that routes only encrypted bytes). This is implemented and exercised only in a loopback + NAT-isolated CI harness — it is not a shippable cross-machine path today. Built

See Package & deploy and Deployment modes for the full picture, and the roadmap for what goes live next.

Can a deployed agent leak my method, or escape its sandbox?

The protections are structural — built into how runs work, not a setting you can misconfigure:

  • A run can only do what it was admitted to do — no ambient power to read, call, retain, reveal, or export beyond the work it was handed. Available
  • A running agent cannot rewrite its own method: the agent definition is editable only from an edit chat, never a work chat, enforced by an OS sandbox at the kernel — so even a shell inside a run cannot change it. Available (Linux/macOS)
  • On Windows, the kernel method-isolation sandbox is not built yet. Planned

These are paired with adversarial tests that fail if the protection is removed. See How GaugeDesk protects your work.

Certs, signing & source

Why are the downloads unsigned?

Code-signing and notarization are being set up. Until then, use the OS override:

System Settings → Privacy & Security → Open Anyway. If macOS says the app is "damaged" and shows no such button, run xattr -dr com.apple.quarantine /Applications/GaugeDesk.app in Terminal, then open it.

At the SmartScreen prompt, choose More info → Run anyway.

Mark the .AppImage executable, or install the .deb.

All releases are on GitHub. Code-signing is a known gap. Planned

Is GaugeWright SOC 2 / ISO 27001 certified?

Not yet. SOC 2 Type II, a DPA with a published subprocessor list, and an independent penetration test are committed and prioritized but not yet available. Planned

Distinguish two kinds of assurance:

  • Structural guarantees — the confidentiality and isolation invariants are stated formally and machine-checked in the codebase today (for example, a relay cannot read payload, a handle is not access). Available
  • Policy / operational assurance — third-party audits, attestations, and a published compliance posture. Planned

See the architecture & security documentation for the invariant→control crosswalk and an honest compliance posture.

Where's the source?

On GitHub. The authoritative specification and the formal models live there, and this documentation lives alongside the code.

Where to go next