Pluely
The Open Source Alternative to Cluely - A lightning-fast, privacy-first AI assistant that works seamlessly during meetings, interviews, and conversations without anyone knowing. Built with Tauri for native performance, just 10MB. Completely undetectable in video calls, screen shares, and recordings.
📥 Download Pluely
🚀 Get the Latest Release
Available formats: .dmg (macOS) • .msi / .exe (Windows) • .deb / .rpm / .AppImage (Linux)
Free plan forever · no account needed to start · updates ship automatically
✨ What is Pluely v1?
Pluely v1 is a ground-up rebuild: one translucent overlay with two modes, Ask and Listen, plus a full dashboard for your chats, meetings, files, prompts, and settings. It's built for the moments where switching to a browser tab would cost you the room: interviews, sales calls, standups, lectures, live debugging.
| 🪶 Lightweight | 🕶️ Invisible | ⚡ Instant |
|---|---|---|
| 9 to 16 MB installer | Hidden from screen shares and recordings | Launches in under 100ms, answers in a tap |
| A fraction of Electron alternatives | No meeting bot, no participant, no trace | Global hotkeys summon it from inside any app |
| Minimal CPU and RAM, even live | Can hide from the Dock and taskbar too | Streaming answers, live transcription |
💬 Ask mode
Type a question, dictate it with push-to-talk, or let Pluely see your screen: capture it, drag-select a region, attach files, or turn on Use image so every message carries a fresh screenshot. Documents go through built-in OCR and stay in context for follow-up questions. Answers stream in as Markdown, and everything is saved locally where you can search, export, or delete it.
🎧 Listen mode
Hit Start and Pluely transcribes your mic and system audio live, with speaker labels and language selection. Automatic responses fire when someone asks a question, after every pause, or only when you tap Suggest. Smart follow-up chips appear under each answer, generated from the actual conversation. Every session is saved as a meeting with its full transcript.
🧰 What else is in the box
- 200+ hosted models on Pro plans: GPT, Gemini, Claude, Llama and more, searchable and switchable mid-conversation, no API keys to manage.
- Free forever with your own keys: connect any LLM or speech-to-text provider through a curl template, or plug in the AI CLIs you already have (Claude Code, Gemini CLI, Codex, Qwen Code, Ollama). No limits from us; it's your account.
- Real stealth: excluded from screen capture, absent from recordings and screenshots, never steals focus from the app you're in, and the icon can disappear from the Dock or taskbar. Details in Stealth & privacy.
- Keyboard-first: global hotkeys for summon, capture, and listening; single keys scroll the answer and transcript once the overlay has focus. Full reference: Overlay shortcuts.
- Private by architecture: chats, meetings, transcripts, and files live in a local SQLite database on your machine. Your own provider keys stay local. Your conversations never train anything.
- Custom prompts with knowledge files, a document library, plan and usage meters, and identical builds for macOS, Windows, and Linux.
📚 Documentation
docs.pluely.com covers every feature, setting, and edge case, with per-OS guides where platforms differ:
📋 Prerequisites
Pluely installs like any normal desktop app. On Linux you need the WebKitGTK runtime that Tauri apps use, see Tauri's prerequisites page for your distro. macOS and Windows need nothing extra: grant the screen and microphone permissions on first run and you're set.