How do I start the server?

In LM Studio, open the Developer tab and start the local server (default port 1234). Load a model, add http://localhost:1234/v1 in Pluely as a custom provider, and the loaded model appears in the picker.

Is my LM Studio API key safe in Pluely?

Yes. Keys are encrypted and stored locally on your device — they never leave your computer except in requests to LM Studio itself. Pluely's servers never see them.

Does Pluely charge for using LM Studio?

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

Which LM Studio models can I use?

Any model the endpoint serves — for example qwen3-14b, gemma-3-27b, llama-4-scout. You choose which ones appear in the overlay's picker.

Can I use LM Studio 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.

LM Studio, in an invisible overlay.

LM Studio runs open models locally with a friendly desktop UI and serves them on an OpenAI-compatible port — the least technical path to a fully offline Pluely. Browse models, click download, connect, done.

Download free Read the setup guide

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

All custom providers

Why LM Studio?

Point-and-click local models.

Local AI without the terminal

LM Studio is the GUI answer to Ollama: search models, see which fit your RAM, download with a click. If the command line isn't your home, this is your local-AI on-ramp.

Hardware-aware model picks

It tells you upfront which quantizations your machine can actually run — no downloading a 70B model just to watch it crawl.

Same privacy as any local setup

Answers are generated on your machine and Pluely stores everything locally — the complete loop happens on hardware you own.

Connection details

Base URL: http://localhost:1234/v1
Download: lmstudio.ai
Example models: qwen3-14bgemma-3-27bllama-4-scout

Start LM Studio's local server (Developer tab) first — no API key needed on your own machine.

Connect LM Studio in three steps

Any OpenAI-compatible endpoint works the same way.

Start LM Studio

Install LM Studio from lmstudio.ai and start its local server — it listens on http://localhost:1234/v1.

Add it as a custom provider

Open Pluely's dashboard → AI Providers → Add Custom Provider. Paste the base URL (http://localhost:1234/v1), and pick the models you want available.

Pick it and ask

Your LM Studio 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 LM Studio

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

Ask LM Studio 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. LM Studio answers with the actual context in front of you.

LM Studio answers your meetings live

Listen mode transcribes your mic and system audio in real time with speaker labels, and LM Studio 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 LM Studio.

LM Studio + Pluely — common questions

More providers that plug in

OpenAI

GPT models on your own key.

Connect it

Anthropic

Claude on your own key.

Connect it

Google AI Studio

Gemini on a free API key.

Connect it

OpenRouter

400+ models behind one key.

Connect it

Groq

The fastest inference on the planet.

Connect it

Mistral AI

European frontier models, free tier included.

Connect it

Put LM Studio over everything.

Install Pluely, paste your local endpoint once, and LM Studio answers for the next error, the next call, the next thing on your screen.

Download free Prefer a CLI?

Free plan forever · Invisible on screen shares · No bot joins your calls

Explore Pluely

Download for your platform, browse release history, or explore our development journey

Platform Downloads

macOS

Apple Silicon & Intel

Download for macOS

Windows

x64 Architecture

Download for Windows

Linux

Debian Package

Download for Linux

Recent Releases

View All Releases

Loading releases...

Browse & Explore

All Downloads

Latest release downloads

View Downloads

Version History

Browse all releases

Browse Version History

Changelog

Development timeline

Browse Changelog

Ready to get started?

Download Pluely now and experience the privacy-first AI assistant that works seamlessly in the background.

Download Now Read the Docs

LM Studio, in an invisible overlay.

Download free Read the setup guide

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

All custom providers

Why LM Studio?

Point-and-click local models.

Local AI without the terminal

LM Studio is the GUI answer to Ollama: search models, see which fit your RAM, download with a click. If the command line isn't your home, this is your local-AI on-ramp.

Hardware-aware model picks

It tells you upfront which quantizations your machine can actually run — no downloading a 70B model just to watch it crawl.

Same privacy as any local setup

Answers are generated on your machine and Pluely stores everything locally — the complete loop happens on hardware you own.

Connection details

Base URL: http://localhost:1234/v1
Download: lmstudio.ai
Example models: qwen3-14bgemma-3-27bllama-4-scout

Start LM Studio's local server (Developer tab) first — no API key needed on your own machine.

Connect LM Studio in three steps

Any OpenAI-compatible endpoint works the same way.

Start LM Studio

Install LM Studio from lmstudio.ai and start its local server — it listens on http://localhost:1234/v1.

Add it as a custom provider

Open Pluely's dashboard → AI Providers → Add Custom Provider. Paste the base URL (http://localhost:1234/v1), and pick the models you want available.

Pick it and ask

Your LM Studio 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.