[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-93868":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":14,"contributorsCount":9,"subscribersCount":14,"size":14,"stars1d":14,"stars7d":14,"stars30d":14,"stars90d":14,"forks30d":14,"starsTrendScore":14,"compositeScore":15,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":16,"fork":16,"defaultBranch":17,"hasWiki":16,"hasPages":16,"topics":9,"createdAt":9,"pushedAt":9,"updatedAt":18,"readmeContent":19,"aiSummary":20,"trendingCount":14,"starSnapshotCount":14,"syncStatus":21,"lastSyncTime":9,"discoverSource":22},93868,"OpenCluely","TechyCSR\u002FOpenCluely","TechyCSR","OpenCluely is a free, open source Cluely (alternative), built for technical interviews like DSA, OAs, and CP. It offers an invisible overlay, real-time AI help, Smart Image Processing for question capture, and multi-language support : 100% customizable and private.",null,"https:\u002F\u002Fgithub.com\u002FTechyCSR\u002FOpenCluely","JavaScript",481,132,0,43.37,false,"main","2026-09-21 04:01:26","\u003Cdiv align=\"center\">\n\n# OpenCluely\n\n**The invisible AI interview copilot.**\n\nReal-time AI help on a stealth overlay that screen sharing cannot see. Ask by voice or screenshot, and get clear answers that stream in as you need them.\n\n\u003Cp>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FTechyCSR\u002FOpenCluely\u002Freleases\u002Flatest\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002FTechyCSR\u002FOpenCluely?style=for-the-badge&label=Latest&color=111111&labelColor=000000\" alt=\"Latest release\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FTechyCSR\u002FOpenCluely\u002Freleases\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002FTechyCSR\u002FOpenCluely\u002Ftotal?style=for-the-badge&color=111111&labelColor=000000\" alt=\"Downloads\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"LICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-111111?style=for-the-badge&labelColor=000000\" alt=\"MIT License\" \u002F>\u003C\u002Fa>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPlatforms-Windows%20%7C%20macOS%20%7C%20Linux-111111?style=for-the-badge&labelColor=000000\" alt=\"Platforms\" \u002F>\n\u003C\u002Fp>\n\n\u003Ca href=\"https:\u002F\u002Fopencluely.techycsr.dev\">\u003Cb>Website\u003C\u002Fb>\u003C\u002Fa>  | \n\u003Ca href=\"#download\">Download\u003C\u002Fa>  | \n\u003Ca href=\"#quick-start\">Quick start\u003C\u002Fa>  | \n\u003Ca href=\"#how-it-works\">How it works\u003C\u002Fa>\n\n\u003C\u002Fdiv>\n\n## Demo\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F896a7140-1e85-405d-bfbe-e05c9f3a816b\n\n## What it is\n\nOpenCluely is a desktop app for technical interviews and practice. It places a small overlay on your screen that recording and conferencing tools do not capture. You can speak a question or take a screenshot, and the AI answers in real time. The answer streams into a floating window and an optional chat panel, with clean code blocks and syntax highlighting.\n\nIt is free and open source. Processing stays on your machine, and the only thing that leaves your device is the request you send to the AI provider.\n\n## Highlights\n\n- **Invisible overlay.** Windows stay out of Zoom, Google Meet, Microsoft Teams, Discord, and OBS captures. You see the answer, the call does not.\n- **Hidden during screen share.** When a share starts, the app can hide every window on its own.\n- **Real-time voice.** Speech is split on natural pauses instead of a fixed timer, so one spoken question stays one question. Filler phrases that Whisper invents on silence are dropped before they reach the model.\n- **Streamed answers.** Replies appear word by word as the model generates them, in both the chat and the floating window.\n- **Direct image analysis.** Screenshots go straight to Gemini for visual reasoning, with no slow OCR step in between.\n- **Session memory.** The whole conversation is remembered, so follow-ups, edge cases, and optimizations keep their context.\n- **Language aware.** Tailored answers for C++, C, Python, Java, and JavaScript.\n- **Stealthy by design.** Runs under ordinary system names, ships with no telemetry, and keeps your session local.\n- **Cross platform.** Pre-built installers for Windows and Linux (.deb and AppImage). macOS runs from source in one command.\n\n## Download\n\nPre-built installers are published with every release. These links always point at the newest version.\n\n| Platform | File | Notes |\n|---|---|---|\n| Windows | [Setup .exe](https:\u002F\u002Fgithub.com\u002FTechyCSR\u002FOpenCluely\u002Freleases\u002Flatest) | NSIS installer. Adds a Start Menu shortcut. |\n| Linux (Debian or Ubuntu) | [.deb](https:\u002F\u002Fgithub.com\u002FTechyCSR\u002FOpenCluely\u002Freleases\u002Flatest) | Pulls system deps automatically (Python, ffmpeg, GTK). |\n| Linux (universal) | [.AppImage](https:\u002F\u002Fgithub.com\u002FTechyCSR\u002FOpenCluely\u002Freleases\u002Flatest) | No install. Run `chmod +x` then launch. |\n\n> **macOS:** there is no pre-built download. The app is unsigned and un-notarized, so macOS Gatekeeper blocks it as \"damaged and can't be opened.\" Run OpenCluely from source instead — see [Quick start](#quick-start). It is a one-line `.\u002Fsetup.sh` once Node.js is installed.\n\nEvery build is produced automatically on GitHub Actions and ships with SHA-256 checksums. Each release also lists the full set of commits it includes.\n\nThe website at [opencluely.techycsr.dev](https:\u002F\u002Fopencluely.techycsr.dev) detects your operating system and offers the right installer directly.\n\n## Quick start\n\nIf you would rather build from source, three steps are all it takes.\n\n1. Clone the repository.\n\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002FTechyCSR\u002FOpenCluely.git\n   cd OpenCluely\n   ```\n\n2. Run the setup script.\n\n   ```bash\n   .\u002Fsetup.sh\n   ```\n\n   The script installs Node dependencies, creates your `.env` from the example, sets up a local Whisper virtual environment, points the config at it, and launches the app.\n\n3. Add your Gemini key.\n\n   On first launch the Settings window opens automatically. Get a free key from [Google AI Studio](https:\u002F\u002Faistudio.google.com\u002F) and paste it in, or edit `.env` directly. Both work, and changes are picked up without a restart.\n\n### Platform notes\n\n- On Windows, use Git Bash (included with Git for Windows) or WSL to run `setup.sh`.\n- On macOS and Linux, your normal terminal works.\n- **macOS users must build from source** (steps above) — there is no pre-built `.dmg`. Because the app is unsigned, a downloaded build would be blocked by Gatekeeper as \"damaged\"; running from source avoids that entirely.\n- No manual `npm` commands are needed. The script handles everything.\n\n### Setup script options\n\n```bash\n.\u002Fsetup.sh --build                # Build a distributable for your OS\n.\u002Fsetup.sh --ci                   # Use npm ci instead of npm install\n.\u002Fsetup.sh --no-run               # Set up only, do not launch\n.\u002Fsetup.sh --install-system-deps  # Install sox for the microphone (optional)\n.\u002Fsetup.sh --skip-whisper         # Skip the local Whisper bootstrap\n```\n\n## Configuration\n\nThe setup script writes sensible defaults. The only required value is a Gemini API key.\n\n```bash\n# Required\nGEMINI_API_KEY=your_gemini_api_key_here\n\n# Optional speech provider. Pick one.\nSPEECH_PROVIDER=whisper\n\n# Azure option\nAZURE_SPEECH_KEY=your_azure_speech_key\nAZURE_SPEECH_REGION=your_region\n\n# Local Whisper option\nWHISPER_COMMAND=whisper\nWHISPER_MODEL_DIR=.whisper-models\nWHISPER_MODEL=turbo\nWHISPER_LANGUAGE=en\n```\n\nSpeech is optional. If no provider is configured, the microphone button hides itself across the app.\n\n## Optional voice setup\n\nYou can use local Whisper for offline transcription or Azure Speech for a cloud option.\n\nFor local Whisper, `.\u002Fsetup.sh` handles the full setup. It creates `.venv-whisper`, installs `openai-whisper`, points `.env` at the virtual environment, creates `.whisper-models`, and runs a quick speech test. You only need Python 3.10 or newer and ffmpeg on your system. Install those with `.\u002Fsetup.sh --install-system-deps`, or add `ffmpeg` and `sox` yourself.\n\nFor Azure Speech, create a Speech resource in the [Azure Portal](https:\u002F\u002Fportal.azure.com\u002F), then add the key and region to `.env` with `SPEECH_PROVIDER=azure`.\n\n## How it works\n\n1. **Ask.** Speak the question or press the screenshot shortcut. The microphone listens for natural pauses on its own and does not cut you off mid sentence.\n2. **Reason.** Gemini reads the audio or image with full conversation context and works toward a precise answer.\n3. **Answer.** The response streams into the overlay in real time, with formatted text and highlighted code.\n\n## Keyboard shortcuts\n\n| Action | Shortcut | Description |\n|---|---|---|\n| Screenshot capture | `Cmd\u002FCtrl + Shift + S` | Capture the screen and analyze it with Gemini |\n| Toggle speech | `Alt + R` | Start or stop voice recognition, if configured |\n| Toggle visibility | `Cmd\u002FCtrl + Shift + V` | Show or hide all windows |\n| Toggle interaction | `Cmd\u002FCtrl + Shift + I` or `Alt + A` | Enable or disable click through |\n| Open chat | `Cmd\u002FCtrl + Shift + C` | Open the interactive chat window |\n| Settings | `Cmd\u002FCtrl + ,` | Open the settings panel |\n\n## Project status\n\nOpenCluely is under active development. The core is stable and improvements ship regularly.\n\n### Done\n\n- Stealth overlay with a draggable command bar and a click through toggle\n- Hidden during screen share, with automatic hiding when a share begins\n- Screenshot capture with direct Gemini analysis, no OCR step\n- Real-time voice input that segments on natural pauses, not a blind timer\n- Utterance coalescing so one spoken question becomes one answer\n- Streamed answers that render word by word in the chat and the overlay\n- Whisper hallucination filter that drops phantom phrases on silence\n- AI response window with markdown and syntax highlighting\n- Global shortcuts for capture, visibility, interaction, chat, and settings\n- Session memory and a full chat UI\n- Language picker and a DSA skill prompt\n- Optional Azure Speech and local Whisper, with an auto hiding mic button\n- Multi-monitor and area capture support\n- Window binding and positioning\n- Settings management with disguise and stealth modes\n\n### Planned\n\n- Multiple model backends alongside Gemini (OpenAI, Anthropic, local)\n- Auto typing of code snippets into editors and IDEs\n- Export of conversation history to markdown or PDF\n- Deeper stealth, including process name randomization\n\n## Troubleshooting\n\n\u003Cdetails>\n\u003Csummary>Setup issues\u003C\u002Fsummary>\n\n- **setup.sh will not run.** Make sure you are in the project folder (`cd OpenCluely`) and that the script is executable (`chmod +x setup.sh`). On Windows, use Git Bash.\n- **Setup stops with exit code 130.** That means Ctrl+C was pressed. Run `.\u002Fsetup.sh` again.\n- **Node or npm not found.** Install Node.js 18 or newer from [nodejs.org](https:\u002F\u002Fnodejs.org\u002F), restart the terminal, and retry.\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>App issues\u003C\u002Fsummary>\n\n- **Electron will not start or shows a blank window on Linux.** Try `npm run dev`, and make sure X11 or XWayland is available in headless setups.\n- **macOS screen capture does not work.** Grant Screen Recording permission under System Settings, Privacy and Security, then relaunch the app.\n- **Windows SmartScreen blocks the app.** Click More info, then Run anyway, or use `npm start` during development.\n- **Microphone or voice not working.** Voice is optional. For Azure, add valid keys to `.env`. For Whisper, install `openai-whisper`, `ffmpeg`, and `sox`, then set `SPEECH_PROVIDER=whisper`.\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\n\u003Csummary> Limitations \u003C\u002Fsummary>\n\n- **Screen-capture invisibility does not work on Linux.** The overlay stays hidden from screen shares and recordings only on **macOS** and **Windows**. This relies on Electron's `setContentProtection`, which maps to `NSWindowSharingNone` on macOS and `WDA_EXCLUDEFROMCAPTURE` on Windows. Electron provides **no equivalent on Linux** (neither X11 nor Wayland), so on Linux the call is a silent no-op and the overlay **will be visible** to anyone you screen-share with. This is a platform limitation, not a bug — there is no window flag on Linux that excludes a window from framebuffer capture. If you need capture-invisibility, run OpenCluely on macOS or Windows. As a partial workaround on Linux, share a single application window instead of your entire screen, or place the overlay on a monitor you are not sharing.\n\n\u003C\u002Fdetails>\n\n\n\n## Privacy and ethics\n\nOpenCluely collects no data and sends no telemetry. Processing happens locally, and your session stays on your device. Requests to the AI provider are encrypted in transit.\n\nThe app is built for learning and practice. You are responsible for following the rules of any interview you take and the policies of the companies involved.\n\n## License\n\nReleased under the MIT License. See [LICENSE](LICENSE) for details.\n\n## Acknowledgments\n\n- Google Gemini for the AI reasoning\n- Azure Speech and OpenAI Whisper for optional voice input\n- Electron for the cross platform desktop runtime\n- [Vysper by varun-singhh](https:\u002F\u002Fgithub.com\u002Fvarun-singhh\u002FVysper) for UI and structure inspiration\n\n\u003Cdiv align=\"center\">\n\nBuilt by [TechyCSR](https:\u002F\u002Ftechycsr.dev). If OpenCluely helped you, consider giving it a star ⭐\n\n\u003C\u002Fdiv>\n","OpenCluely 是一款面向技术面试场景的开源桌面辅助工具，专为算法题（DSA）、在线笔试（OA）和编程竞赛（CP）设计。它通过不可被录屏\u002F会议软件捕获的隐形浮动窗口，提供实时语音提问、截图识别（直连 Gemini 视觉模型，跳过 OCR）、流式 AI 答案输出、多语言代码适配（C++\u002FPython\u002FJava 等）及本地会话记忆功能，所有数据处理默认在本地完成，仅用户主动发送的请求上传至 AI 服务商。适用于求职者在真实技术面试或日常刷题中获取低干扰、高隐私的即时解题支持。",2,"trending"]