Personal AI

Evidence state (2026-09-24, v0.41.0): Personal AI is available, not yet lifecycle-verified. The current release declares its components (Ollama and Open WebUI), and no automated lifecycle run covers install, apply, verify, backup, or restore yet. Runtime evidence is pending.

Personal AI runs a chat interface for language models on your Linux Docker host. The local owner receives the initial administrator account, public signup is disabled, and no kombify account is required. The release catalog calls this use case Private AI and delivers it as the optional ai workload with the private-ai alternative.

Applications

Ollama serves the model.
Open WebUI provides the chat interface you sign in to.

This page covers both, because they are selected and operated together.

Optional applications in v0.54.3

The synced release also declares AnythingLLM as another chat alternative, and separate add-ons for Hermes Agent, Paperclip, OpenHands, Docling, Apache Tika, LiteLLM, ComfyUI and SearXNG. These are applications on your own host; their module contracts do not expose kombify’s internal AI services. The released application catalog lists each selection, module and compute profile. Select them explicitly and review their credentials, accelerator requirements and permissions before applying. The optional SpeechKit server entry is still backed by an unreleased placeholder image. It is excluded from available server claims even though a module contract exists. This does not change the availability of the separately released SpeechKit clients.

Check your host capacity first

The CPU profile has a declared host floor of 4 CPU cores, 12 GiB RAM, and 40 GiB disk; 8 CPU cores, 16 GiB RAM, and 80 GiB disk are recommended. Model size matters on top of that floor:

Ollama has a declared 6 GiB RAM limit. The downloaded model weights plus the context you use must fit inside it.
Open WebUI has a declared 2 GiB RAM limit.
Allow disk space for container images and for downloaded model weights together.
A higher compute tier uses the same CPU runtime. The v0.54.3 module contract separately declares experimental NVIDIA and AMD accelerator profiles; selecting a higher compute tier alone does not enable one.

These limits describe capacity, not response speed. Check the available host resources and the chosen model’s requirements before installation. See Choose a StackKit for compute profiles.

Select the AI workload

From an empty owner workspace:

stackkit init basement-kit --platform standalone-compose \
  --use-case ai --use-case-alternative ai=private-ai \
  --use-case-alternative basement-core=standalone \
  --module-compute-profile stackkits-basement-core-runtime=standard \
  --module-compute-profile stackkits-private-ai-runtime=standard \
  --owner-source=local --non-interactive

The init command creates the AI configuration and its private credential references. When adding AI to an existing workspace, update the StackSpec and run stackkit secrets materialize. Review and apply the configuration:

stackkit validate
stackkit generate
stackkit plan --json
stackkit apply
stackkit verify

Run Apply on the supported Linux host using its observed inventory; see Review, plan, and apply.

Open the AI route as the owner

After apply, open the generated AI route. Open WebUI creates its initial administrator from the established local owner’s identity and the owner-password secret that the init command placed in owner custody. From your StackKits workspace, retrieve the initial password in a private terminal:

stackkit secrets reveal --workload ai --slot owner-password

Keep the displayed password private and do not copy it into chats, screenshots, or Git.
Change the password inside Open WebUI after the first login. The startup bootstrap does not reset an existing account, so keep your changed administrator password in your own custody.

Choose and download a model explicitly

No model is selected or pulled for you, not during install, restart, or upgrade. In Open WebUI, open Admin Settings, explicitly select an Ollama model, and request its download. Before you pick one, review the upstream model’s license, download size, quantization, context length, and RAM requirements. Start with a small model on the CPU profile. Larger models and longer contexts need more memory. A model that downloads successfully may still exceed the available inference capacity. Ollama’s API has no host-published port. Open WebUI reaches it on the private workload network. Ollama has outbound network access for requested downloads.

Ask your first question

Create a new chat in Open WebUI, select the downloaded model, and send a question. The model runs on your host. Reopen the chat to check that your conversation was saved.

Use your model from your kombify account (optional)

You can also use this Ollama from the AI chat in your kombify account without opening any inbound port. An optional connector next to Ollama opens an outbound tunnel to kombify. kombify never connects into your network, and requests on your own model do not count against your Cloud AI allowance.

In your kombify account, open Settings → AI access → Your model endpoints and add an endpoint. Choose kombify Local AI StackKit as the location.
Copy the connector token that is shown once.
On the host, from your StackKits workspace, turn on the connector and paste the token when prompted, then apply:

stackkit setup ai-connect --token-file -
stackkit generate
stackkit apply

Back in Settings → AI access, select Check connection. The endpoint shows as online and lists the models you downloaded.
In a chat, choose My endpoint as the AI source. This is a direct chat with your model; it has no agent tools.

Only the model list, model details and chat completion requests reach Ollama through the connector; model downloads and deletions stay local. To stop using it, delete the endpoint in Settings → AI access, which makes the token useless everywhere, and turn the connector off on the host:

stackkit setup ai-connect --disable
stackkit generate
stackkit apply

What persists where

Storage is split deliberately:

What	Where	Backup behavior
Chats and Open WebUI data	Persistent `open-webui-data` volume at `/app/backend/data`	Declared backup source; complete AI restoration remains unverified
Downloaded model weights	Persistent `ollama-models` volume at `/root/.ollama`	Not a backup source; excluded from backups

Chats and model weights persist across container replacement. Keep the model name and digest so you can identify it again if its storage is lost. Model availability depends on its upstream source. Complete AI backup and restoration remain unverified; container persistence alone does not establish recovery. See Back up and restore for the workspace lifecycle.

Troubleshooting

State	What to do
Apply blocks the host with a capacity reason	Check the host floor above; does the host meet the 4 CPU / 12 GiB / 40 GiB floor and does the model you intend to load fit the 6 GiB Ollama limit?
Initial administrator login fails	Use the owner’s email and initial password for the first login. After changing it, use your new password; restarting does not reset an existing account.
A previously downloaded model is missing	Check the selected model and the persistent model volume. Ordinary container replacement preserves it. A new or lost model store requires an explicit download.
Responses stall or the container stops	Check workload logs and available memory. A smaller model or shorter context reduces memory use; CPU inference may also take time.
Your kombify account shows the endpoint as offline	The connector is not running. Check that the connector token was set up and the workload was applied; the Node Hub shows the connector container.
Your kombify account says the model is not installed	Download the model in Open WebUI first; only models that Ollama already has are listed.
AI owner secret references missing in an existing workspace	After changing the canonical intent, run the existing `stackkit secrets materialize`; generation alone does not mint secrets.

If a question is not covered above, check the Node Hub status for the workload containers before changing anything in the generated runtime directory.

Get the apps

Open WebUI is browser-based: open your generated AI route in any modern browser and sign in with the administrator account you set. No client installation is required.

Ollama

Ollama itself is a CLI/API model runner rather than an end-user app. StackKits already runs it for you; the upstream site documents the model catalog and CLI if you want to inspect it directly on the host.

Get started

Get help

Guides

Reference

Applications

Optional applications in v0.54.3

Check your host capacity first

Select the AI workload

Open the AI route as the owner

Choose and download a model explicitly

Ask your first question

Use your model from your kombify account (optional)

What persists where

Troubleshooting

Get the apps

Ollama

​Applications

​Optional applications in v0.54.3

​Check your host capacity first

​Select the AI workload

​Open the AI route as the owner

​Choose and download a model explicitly

​Ask your first question

​Use your model from your kombify account (optional)

​What persists where

​Troubleshooting

​Get the apps

Ollama

Applications

Optional applications in v0.54.3

Check your host capacity first

Select the AI workload

Open the AI route as the owner

Choose and download a model explicitly

Ask your first question

Use your model from your kombify account (optional)

What persists where

Troubleshooting

Get the apps