Skip to content

Deploy your AI where the cloud can’t go.

Ghost runs your product on an open model inside your customer’s network. No internet.

Customers

6 on-prem sites. 4 on the latest release.

Build update
SiteVersionStatus

Regional bank

2.4.02.3.0Updating to 2.4.0Rolled back

State agency

2.3.0Update ready

Hospital network

2.4.0Running

Defense supplier

2.4.0Running

Electric utility

2.4.0Running

Insurance carrier

2.4.0Running
Regional bank, on-prem server, no internet
$ ghost up acme-copilot-2.4.0.ghost  currently running 2.3.0✓ vendor key e208441de2f697d1✓ signature and all 19 files verified✓ services running  running 1 evals    ✗ contract summary: answer does not contain "30 days"✗ evals failed; rolling back to 2.3.0✓ 2.3.0 is running again
Illustrative Ghost console listing six on-prem customer sites, with a terminal from our working demo showing a failed upgrade at a regional bank rolled back automatically.

For AI companies selling to

  • Banks
  • Hospitals
  • Law firms
  • Defense
  • Utilities
  • Government
  • Insurers

How it works

  1. 1

    Take it off the API

    Swap OpenAI or Claude for an open model. Ship it as one signed file.

    Building in your CI

    acme-copilot 2.4.0

    • OpenAI and Claude calls routed to a local open model
    • App images from docker-compose.yml
    • Model weights and eval suite
    • Exact image IDs and model commits recorded
    • Signed with vendor key e208441de2f697d1

    Built acme-copilot 2.4.0 → acme-copilot-2.4.0.ghost (19 files, 96.1 MB)

  2. 2

    Cross the gap

    Their IT team imports it. Nothing connects back.

    Your CI

    Online

    Regional bank

    No internet

    Air gap2.3.0-to-2.4.0.update.ghost
    Full release96.1 MB
    Update2.2 MB

    Update 2.3.0 → 2.4.0: 2.2 MB instead of 96.1 MB (2.3%).

  3. 3

    Prove it, keep it running

    Your evals run on their servers. A failed upgrade rolls back.

    Regional bank, on-prem admin

    acme-copilot 2.4.0

    Running
    Evals against your cloud baseline24 / 24
    • 09:12Update 2.4.0 imported by IT
    • 09:14Signature verified, 19 files
    • 09:15Evals passed, 24 of 24
    Approve next updateExport support bundle

Tested on real AI apps

  • Ghost demo 2.3.0 → 2.4.0

    App and 2 models

    Release 96.1 MB, update 2.2 MB. Update is 2.3%

  • n8n self-hosted AI starter kit 1.115.0 → 1.116.0

    n8n, Ollama with llama3.2:1b, Qdrant, Postgres

    Release 3.7 GB, update 268.2 MB. Update is 7.2%

  • Langfuse 4.75.0 → 4.76.0

    7 services

    Release 955.2 MB, update 389.5 MB. Update is 41%

  • Flowise 3.1.3 → 3.1.4

    1 image

    Release 1.5 GB, update 1.5 GB. Update is 97%

Full releaseUpdateMeasured Nov 6, 2026.

Three commands.

# once: your signing key; CI reads it from GHOST_KEY$ ghost keygenWrote ~/.ghost/vendor.key (keep private; in CI, set GHOST_KEY) and ~/.ghost/vendor.pub (give to customers).Key ID e208441de2f697d1# every release: reads ghost.yaml and your docker-compose file$ ghost buildhashing 19 filesBuilt acme-copilot 2.4.0 → acme-copilot-2.4.0.ghost (19 files, 96.1 MB)

Works with what you already run.

Ghost works with open models such as Llama, Qwen, Mistral, Gemma, DeepSeek and gpt-oss; runs on Docker Compose, Hugging Face, Ollama, NVIDIA GPUs and Linux with your evals and CI; and is tested with open-source AI apps including n8n, Langfuse, Flowise, open-webui, Dify, RAGFlow, LibreChat, AnythingLLM and Khoj.

From cloud API to their server.

  1. 01

    Check

    Free

    We find what breaks offline.

  2. 02

    Convert

    Fixed price

    We swap in an open model, tuned on your data.

  3. 03

    Run

    Monthly

    Signed updates. Automatic rollback if evals fail.

We stay on until it ships.

Every customer site, every update, with you.

Questions

Our product runs on OpenAI or Claude. Can it still run offline?

Yes. We swap in an open model tuned on your data.

Will an open model be as good?

Often close. We measure it on your tests first.

How is this different from Replicated or Zarf?

They’re built for Kubernetes. Ghost starts from your docker-compose file.

What hardware does my customer need?

Usually one Linux server with an NVIDIA GPU.

Got a deal stuck on on‑prem?

Send us your docker-compose file. Within a week, you’ll know what breaks offline.