CLI integration or local server — which should I use?

Either works. The CLI integration is zero-configuration; the server route (this page) gives you explicit control over the endpoint and works with tools that share the same Ollama instance. Same models, same privacy, pick the workflow you prefer.

Is my Ollama (local server) API key safe in Pluely?

Yes. Keys are encrypted and stored locally on your device — they never leave your computer except in requests to Ollama (local server) itself. Pluely's servers never see them.

Does Pluely charge for using Ollama (local server)?

No. Custom providers are unmetered and fully covered by the free plan — you pay only nothing (it runs on your hardware).

Which Ollama (local server) models can I use?

Any model the endpoint serves — for example llama4, qwen3, gemma3, deepseek-r1. You choose which ones appear in the overlay's picker.

Can I use Ollama (local server) alongside Pluely's bundled models?

Yes. On Pro plans the picker shows your custom providers next to the 200+ bundled models; on the free plan your own providers and CLIs power everything.

Ollama (local server), in an invisible overlay.

Beyond the CLI integration, Ollama also serves an OpenAI-compatible API on localhost — add it as a custom provider and every model you've pulled appears in Pluely. Answers generated on your own silicon, nothing leaving the machine.

Download free Read the setup guide

Your key, encrypted on-deviceUnmetered — free plan covers itOpenAI-compatible

All custom providers

Why Ollama (local server)?

Your local models as a provider endpoint.

Air-gapped by default

The request never touches a network. For regulated work, client NDAs, or plain principle, localhost:11434 is the only endpoint that can't leak anything.

Zero marginal cost

No tokens, no bills, no quotas. Ask Pluely a thousand questions a day and the only cost is watts.

Model of the week, yours immediately

ollama pull <model> and it's in Pluely's picker. The open-model scene moves fast; a local setup means you never wait for a provider to add the new thing.

Connection details

Base URL: http://localhost:11434/v1
Download: ollama.com
Example models: llama4qwen3gemma3deepseek-r1

No API key needed — it's your own machine. Use any non-empty string if a key field is required.

Connect Ollama (local server) in three steps

Any OpenAI-compatible endpoint works the same way.

Start Ollama (local server)

Install Ollama (local server) from ollama.com and start its local server — it listens on http://localhost:11434/v1.

Add it as a custom provider

Open Pluely's dashboard → AI Providers → Add Custom Provider. Paste the base URL (http://localhost:11434/v1), and pick the models you want available.

Pick it and ask

Your Ollama (local server) models now appear in the overlay's model picker. Select one and every Ask, screenshot, and meeting answer runs on your machine — unmetered by Pluely.

Everything Pluely does, on Ollama (local server)

Connecting a provider doesn't limit the product — every mode routes through it.

Ask Ollama (local server) about your screen

Capture the full screen, drag-select just the error or the clause that matters, attach PDFs and documents with built-in OCR, or turn on Use image so every message carries a fresh screenshot. Ollama (local server) answers with the actual context in front of you.

Ollama (local server) answers your meetings live

Listen mode transcribes your mic and system audio in real time with speaker labels, and Ollama (local server) drafts the suggested answer before the question finishes — automatically on every question, after each pause, or only when you tap Suggest.

Summaries, transforms, and notes

One tap turns any answer, transcript, or document into a summary, key points with action items, a translation, or a longer draft — and meeting notes build themselves as you go. All of it runs on Ollama (local server).