Natively-AI-assistant/natively-cluely-ai-assistant

Natively — Free open-source AI meeting assistant, interview copilot, and note taker. The best alternative to Cluely, Otter, Granola, Final Round AI, Fireflies, and Interview Coder. Real-time transcription, AI meeting notes, lecture recording, local RAG, BYOK, and stealth mode. Runs locally. No subscriptions. No data breaches.

What it solves

Natively provides a private, local-first AI assistant designed for high-stakes meetings and interviews. It addresses the privacy concerns and high costs associated with commercial interview-copilot services by running locally, allowing users to use their own LLM keys, and providing advanced stealth features to avoid detection during screen-shared sessions.

How it works

The application uses a Rust-based architecture for low-latency audio capture and processes speech-to-text (STT) entirely on-device using optimized models like Whisper or Apple's native speech frameworks. It maintains a local context window and uses SQLite-based vector search for RAG (Retrieval-Augmented Generation) to recall meeting details. The software includes an "Undetectable" mode that disguises the application process and hides its windows from screen-sharing software, while providing real-time AI-generated suggestions and visual diagrams during live calls.

Who it’s for

This tool is designed for professionals and job seekers who need real-time AI assistance during interviews or meetings and prioritize data privacy, local control, and the ability to use various LLM providers without recurring subscription fees.

Highlights

  • Local-First Privacy: Runs entirely on-device with no cloud data storage, eliminating the risk of data breaches common with centralized services.
  • Advanced Stealth: Includes process-level disguise and window-hiding capabilities to remain invisible during screen shares and in system process lists.
  • Visual Answers: Automatically generates live system design diagrams, flowcharts, and charts based on meeting context.
  • Flexible LLM Support: Allows users to connect their own API keys (OpenAI, Claude, Gemini) or run models locally via Ollama.
  • Low-Latency Performance: Optimized for sub-500ms response times using Rust and zero-copy audio processing.

Related

  • Project
    Laxcorp-Research/project-raven

    An open-source meeting copilot that provides real-time AI assistance and automated recaps using local storage and user-provided API keys for transcription and LLMs.

  • Project
    Blueturboguy07/cue

    An open-source AI copilot that floats over your screen and remains invisible during screen shares, providing real-time assistance for meetings and coding.

  • Project
    fastrepl/anarlog

    anarlog is an open‑source, local‑first meeting‑note app that records audio on your device, transcribes it with on‑device or user‑chosen STT models, and lets you generate AI summaries or chat using any LLM you control. All notes and recordings stay in a local SQLite database (exportable to Markdown) unless you opt‑in to encrypted CloudSync. Built with Tauri (Rust backend) and React/TypeScript, it runs on macOS, Windows, Linux, and has mobile/watch companions. MIT‑licensed for the community code, with optional commercial enterprise components.

  • Project
    iamsrikanthnani/pluely

    An invisible AI desktop overlay that provides real-time transcription and grounded answers during live calls and tasks, remaining hidden from screen shares.

  • Project
    bigsk1/voice-chat-ai

    A modular voice-chat framework that connects various LLM and TTS providers to enable real-time, interactive spoken conversations with AI characters.