Build with llamay

By industry

What changes when the text you are sending a model is a patient record, a trade, a case file or a classified document. The architecture that matters is the same in every one of these: the model runs where the data already is, and nothing crosses a boundary you did not choose.

llamay holds no certifications. It is not HIPAA-certified, not FedRAMP-authorised, not SOC 2 attested, and carries no CE mark. Nothing on this page is a compliance claim, because software cannot make one on your behalf — an obligation belongs to the organisation processing the data.

What llamay offers is architectural: run it on hardware you control and no prompt, document or response reaches a third party, because there is no third party in the path. That removes a whole category of question from your assessment. It does not answer the assessment.

The one property that matters

A HOSTED API your data records, filings a vendor another estate crosses a boundary · needs a processor agreement, a retention answer and a jurisdiction answer LLAMAY, ON YOUR HARDWARE your data records, filings the model same machine no boundary crossed · nothing to agree, nothing to retain elsewhere, no third jurisdiction
The question is not whether a vendor is trustworthy. It is whether the question has to be asked.

Running with no network at all

llamay has no telemetry, no licence check and no call home. A machine with the binary and a model file needs nothing else, which is what makes an air-gapped deployment ordinary rather than a special build. 

# On a connected machine, once:
llamay pull qwen2.5:7b
llamay models path                 # where the weights landed

# Copy the binary and that directory to the isolated machine, then:
llamay serve --addr 127.0.0.1:11435

Weights are content-addressed, so a file copied by hand verifies the same way a downloaded one does. Models and formats covers the store layout.

Financial services

The work. Summarising filings and research, drafting and reviewing credit memos, extracting terms from contracts, classifying transactions, answering questions over an internal document set.

What llamay changes. Material non-public information, positions and client identifiers never leave the estate, so the model is not a new recipient in your data map. Deployments can be per-desk, which keeps an information barrier a physical fact rather than a policy applied to a shared endpoint.

Practically. Use JSON Schema output for extraction so a downstream system gets a typed object rather than prose to parse. Log the model name and version alongside every generated artefact — llamay version prints a build revision, and reproducing an answer later means knowing what produced it.

Healthcare and life sciences

The work. Drafting clinical documentation, summarising literature, structuring trial protocols, coding encounters, answering questions over a formulary or a set of standard operating procedures.

What llamay changes. Patient data and identifiable health information stay on the hardware you already control and already assessed. There is no sub-processor to add, no cross-border transfer to justify, and no retention question about a prompt held by somebody else.

Practically. Run one instance per environment rather than sharing one across research and clinical use — separation of duties is easier to demonstrate than to argue. Pin a model version and record it with each output; a regulator asking why a document says what it says is asking about a specific set of weights.

A model that drafts clinical text is a drafting aid and not a decision. Where an output informs care, the clinical review that already exists is the control, and llamay does not change that.

Defence and government

The work. Summarising and searching document sets, drafting on classified networks, translation, structuring reports.

What llamay changes. It is one static binary with no dependencies, no interpreter and no network requirement, which is the shape an accreditation process can actually inspect. Cross-compiled builds for six platforms come from one source tree, and every release is published with checksums.

Practically. Transfer the binary and the model store through whatever your process already uses for signed artefacts. Nothing has to be reachable from the internet at install time or afterwards.

Security operations

The work. Triaging alerts, summarising incidents, explaining a sample or a log excerpt, drafting detections, answering questions over runbooks.

What llamay changes. Indicators, internal topology and unreleased vulnerability detail are exactly the material an organisation does not want sitting in somebody else's prompt history. Running locally removes that exposure, and it means analysis still works when the incident you are handling is a network one.

Practically. The Ollama-shaped routes mean existing SOAR tooling written against Ollama works without modification. Use a forked context to hold a large runbook once and branch it per alert rather than resending it on every triage.

The work. Review, summarisation, clause extraction, drafting from precedent, answering questions over a matter's documents.

What llamay changes. Privilege survives because nothing is disclosed to a third party. For a firm, that removes the awkward question of whether a vendor's terms are compatible with a duty of confidentiality.

The pattern underneath all of them

Every section above is the same architecture with a different regulator's name attached. If you take one thing from this page, take the shape:

  1. Run it where the data already is. A model reaching the data is cheaper to assess than data reaching a model.
  2. Pin the model and record it. An output you cannot attribute to a specific set of weights is an output you cannot defend later.
  3. Constrain the output. A schema turns a generated answer into a typed object something else can validate.
  4. Keep the human control you already have. llamay produces drafts. Whatever reviews drafts today should still review these.

Where to go next