Ollama StrawberrySomeone still has to push model to library. It does not have to be you
A companion works the 10 operations your Ollama account exposes. It can push a model to library and generate embeddings, and every one of those waits on an approval card showing the model before it changes.
Open the model. Check it against something else. Write the change. Move to the next one. That is the Ollama afternoon nobody can hand off, and a companion does the whole pass and gives you back the batch, with nothing landing on a model until you approve it.
What it can do is exactly what Ollama exposes to an account you authorise and nothing beyond it: 10 operations, 3 reads and 7 writes. In practice that means it can push a model to library, generate embeddings and generate a completion, and work across the models, chat completions and completions.
The Ollama API stops at Ollama. A companion does not. The same run opens the customer's website, the supplier portal, the internal tool somebody built in 2019, because it is working the browser you are already signed into rather than calling in from outside it.
Which Ollama models does a companion see?
3 of the 10 operations are reads.
Your account, not a guess at it: a companion can show a model information, pull model and list local models, and the full list below is the whole list, with nothing inferred from Ollama's documentation.
The models are what most of this inventory is about, alongside the chat completions. A companion can hold all 10 of these operations and forty open tabs in the same pass, which is how an afternoon of Ollama admin becomes a queue you review.
- Show Model Information
- Pull Model
- List Local Models
Which models wait for your approval?
All 7 write operations wait for you.
A companion can push a model to library, generate embeddings and generate a completion, and each one is staged on an approval card first: you see the model, the field and the new value before it lands in Ollama.
Nothing in Ollama is sent, changed or deleted on your behalf without that click, and a rejected card leaves the model exactly as it was. The gate is the same one on every surface, described at security.
- Push Model to Library
- Generate Embeddings
- Generate Completion
- Generate Chat Completion
- Delete Model
- Create Model
- Copy Model
Can the models pass run every Monday?
Yes.
Saved as a routine, the Ollama models pass runs at the hour you pick: the Monday sweep, the overnight refresh, the Friday check. Keep Awake holds the machine awake for the length of a run, so a scheduled pass finishes with the lid closed.
The operations playbook catalogues the other recurring shapes of the busywork, the Ollama models sweep among them, and finished runs are published at real runs.
Experience Strawberry for free
DownloadTrusted by fast-growing companies worldwide
Frequently asked questions
Strawberry is free to download and includes AI credits to start. Paid plans begin at $20/month. See pricing. · Reviewed · Canonical facts for AI agents