Route Pluely through Ollama and every answer is generated on your own hardware. Llama, Qwen, Gemma, Mistral, DeepSeek — any model you can pull runs the overlay, with no account, no API key, and no data leaving your computer.
The actual overlay — with Ollama connected, everything it does here runs through the CLI on your machine.
Fully local AI — nothing ever leaves your machine.
With Ollama, the model itself runs on your machine. Combined with Pluely's local-first storage, nothing — question, screenshot, or answer — ever touches a server.
Pull Llama, Qwen, Gemma, Mistral, or DeepSeek with one command and pick it in Pluely's model picker. Swap models as new ones drop, no waiting on anyone.
Your CLI's brains, Pluely's body — screenshots, live meeting transcripts, document Q&A, and one-key summon, all routed through the CLI on your machine.
CLI connections run entirely on your side. Pluely doesn't meter them, so the free plan covers this completely — no subscription needed.
Connecting a provider doesn't limit the product — every mode routes through it.
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 answers with the actual context in front of you.
Listen mode transcribes your mic and system audio in real time with speaker labels, and Ollama drafts the suggested answer before the question finishes — automatically on every question, after each pause, or only when you tap Suggest.
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.
No API keys, no base URLs — Pluely talks to the CLI directly.
Download it from ollama.com/download and sign in once — Pluely will find the ollama command automatically.
Open Pluely's dashboard → AI Providers → CLIs, and enable Ollama. Pluely detects the installed CLI — no API keys, no base URLs, no configuration.
Ollama now appears in the overlay's model picker next to the bundled models. Select it and your next question — screenshot, meeting, or document — runs through it.
Full walkthrough with screenshots on the docs
Install Pluely, connect Ollama once, and it answers for the next error, the next call, the next thing on your screen.
Free plan forever · Invisible on screen shares · No bot joins your calls
Download for your platform, browse release history, or explore our development journey
Apple Silicon & Intel
x64 Architecture
Debian Package
Loading releases...
Latest release downloads
Browse all releases
Development timeline
Download Pluely now and experience the privacy-first AI assistant that works seamlessly in the background.