Use case · Deployment

An AI employee for networks that never touch the internet

Regulated industry, sovereign cloud, or plain caution: Hedy runs fully air-gapped with local models. Same skills, same governance — zero external calls. Licences validate offline via Ed25519 signatures.

Hedy runs fully air-gapped: point it at a local model server (vLLM or Ollama) and no request ever leaves your network. Knowledge, memory, and audit logs live in your own Postgres. Licensing is offline via Ed25519 signatures, so there are no license callbacks, no sub-processors, and no phone-home. You get the same AI employee and the same governance (append-only audit, L0/L1/L2 approvals, deny-by-default writes, per-asker ACL retrieval) with zero egress.

Last updated: 20 July 2026

How Hedy runs it

01

Local models

Point the gateway at vLLM or Ollama inside the boundary. Anthropic and OpenAI-compatible APIs work identically.

02

Offline everything

Knowledge base, embeddings, memory, audit and metering are all in your PostgreSQL. No external dependency at runtime.

03

Same governance

Approval tiers, allowlists, conduct tests and the audit ledger work identically offline.

04

Verifiable isolation

Bind-address configuration and the absence of external endpoints are auditable in the compose file itself.

Governed by design

  • Licences validate offline via Ed25519 signatures
  • Updates arrive as versioned images you carry across the boundary
  • The eval gate runs on-site, so quality is proven inside the wall

In depth

Air-gap is a deployment mode, not a stripped-down tier. Hedy uses bring-your-own model keys, and "your key" can point at a local vLLM or Ollama endpoint inside your subnet. Every LLM call routes through the Hedy LLM proxy, which is the single metering and quota chokepoint. When the model is local, that proxy talks only to your inference server. There is no outbound call to any hosted model API, and no path where a prompt, a document, or a memory leaves the perimeter.

Your data stays where you can inspect it. Retrieved knowledge, the employee's long-term memory, usage counters, and the audit trail are all written to your Postgres. Nothing is stored in a vendor cloud because there is no vendor cloud in the loop and no sub-processors. This is the core difference from a cloud AI coworker that lives in Slack or Teams: those move your context to someone else's infrastructure to function. Hedy is one AI employee running on yours, doing a team's worth of output without exporting a byte.

Licensing works offline too. Entitlements are carried in an Ed25519-signed license file that Hedy verifies locally against a public key. No activation server, no periodic checkin, no kill-switch that depends on reaching the internet. You can deploy into a network with no route out at all and the product still boots, validates, and runs. A roughly 30-minute Docker Compose install gets you from nothing to a working air-gapped employee.

Governance is identical in air-gap mode, because governance is code and config, not a hosted service. Audit logs are append-only with no update or delete API. Write actions are deny-by-default and require whitelisting, gated by L0/L1/L2 approval tiers. Retrieval is scoped by the asker's ACL, so an answer never surfaces documents the person asking isn't cleared to see. The evidence gate still forces answers to quote their sources verbatim. Cutting the network cord removes egress risk without loosening a single control.

Questions

Can Hedy run with no internet access at all?
Yes. In air-gapped mode Hedy points at a local vLLM or Ollama model server, and all LLM calls route through the on-prem LLM proxy to that server only. Licensing is offline via Ed25519-signed files verified against a local public key, so there is no activation server or phone-home. Knowledge, memory, and audit all live in your Postgres. Nothing requires outbound network access.
Where does my data live if I self-host Hedy air-gapped?
Entirely in your own Postgres on your infrastructure. Retrieved knowledge, the employee's memory, usage metering, and the append-only audit log are all stored locally. There are no sub-processors and no vendor cloud in the data path. Because the model is a local vLLM or Ollama endpoint, prompts and documents never leave your network.
How does licensing work without a connection to a license server?
Hedy uses Ed25519 offline licensing. Your entitlement is a signed file that Hedy verifies locally against a public key at boot, with no callback to any server and no periodic online checkin. This means you can deploy into a fully isolated network and the product still validates and runs normally, with no dependency on reaching the internet.
Do I lose any governance controls when I go air-gapped?
No. Governance is enforced in code and config, so it is identical in air-gapped mode. You keep append-only audit logs with no delete API, deny-by-default write actions with whitelisting, L0/L1/L2 approval tiers, per-asker ACL-scoped retrieval, and the evidence gate that requires answers to quote sources verbatim. Removing network egress tightens security without weakening any control.

Related

hedy.one

See it on your own infrastructure.

Book a demo