bhoot.sh: I Put the Ghost of a Frustrated Indian Senior Dev on My Desktop (100% Local with Gemma 2)

A developer built bhoot.sh, a frameless, transparent PyQt6 desktop companion that runs entirely locally on Gemma 2 (gemma2:2b) and monitors clipboard contents and active window titles to detect bad coding habits. The ghost tracks the mouse cursor with trigonometric vector calculations, escalates its Hinglish and English roasts in severity as repeated offenses are logged to MongoDB, and scans for leaked secrets such as sk-* and ghp_* tokens without sending clipboard data to the cloud.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine https://dev.to/challenges/hacktoberfest-week4-2026-10-26 When I looked at the "Ghost in the Machine" prompt, I noticed almost everyone was building haunted CLI shells or digital memory altars. As an Indian developer, my mind immediately went to a different kind of horror: the evolutions of Indian ghost cinema—and the terrifying spirit of a fed-up senior developer watching you copy-paste from Stack Overflow at 2:00 AM. Classic Indian horror evolved from melodramatic spirits in ancestral havelis Mahal , 1949 and Ramsay Brothers folklore into modern, self-aware "Good Ghosts" Stree , Bhoot who haunt you with lived realities rather than cheap jump scares. Simultaneously, I was inspired by the floating interactive "Loony" lobby companion from Brawl Stars cite: 1 . So I combined the two and built bhoot.sh "Bhoot" = Ghost in Hindi/Marathi : a frameless, 60 FPS transparent desktop wraith that literally possesses your Windows OS, stalks your IDE peripheral vision, tracks your mouse cursor with glowing hollow eyes, and roasts your bad coding habits out loud in Romanized Hinglish and English cite: 7, 8, 9 . bhoot.sh Actually Does on Your Screen: PyQt6 desktop entity whose glowing pupils calculate trigonometric vectors math.hypot to follow your mouse cursor across the screen in real time. Instead of blocking the code you are actively typing, it glides to targeted IDE zones: short → medium → long : VoidDimmer across your entire monitor whilelocal gemma2:2b System32 / Git branch deletion warning before laughing at you. ai.inference on Local Gemma 2 : bhoot sh.coding sins : A reincarnated, highly judgmental senior developer haunting your desktop. Built for the Hacktoberfest 2026: Ghost in the Machine challenge, bhoot.sh is a frameless, transparent desktop wraith that monitors your clipboard and active windows 100% locally—roasting your bad coding habits in Hinglish and English . If you copy-paste from Stack Overflow for the tenth time, accidentally copy a live API key, open Instagram Reels near a deadline, or push "fix bug" straight to main , this phantom glides across your screen, locks its glowing eyes onto your mouse cursor, dims your monitor blood-red, and yells at you. I designed bhoot.sh around a hybrid local-first architecture so that the UI remains butter-smooth at 60 FPS while monitoring system-level events without ever freezing or leaking private clipboard data to the cloud cite: 9 . +-----------------------------------------------------------------------+ | WINDOWS DESKTOP / IDE | | Clipboard pyperclip Window Titles pygetwindow Cursor | +-------------+----------------------------+--------------------+-------+ | | | v v | +-------------------------------------------------------+ | | src/watcher.py Background QThread | | | • Regex Secret Scanner sk- , ghp , mongodb+srv:// | | | • Distraction Tab Detector Reels, YouTube, X | | | • Terminal Crash & Console.log Detector | | +---------------------------+---------------------------+ | | | v | +-------------------------------------------------------+ | | src/memory.py MongoDB Atlas + Local | | | • Logs sin category & timestamp to bhoot sh.sins | | | • Escalates severity: 1=SHORT - 2=MEDIUM - 3+=LONG | | +---------------------------+---------------------------+ | | | v | +-------------------------------------------------------+ | | src/ghost brain.py + GemmaWorker Async QThread | | | • Tier 1-3: Instant lookup from scenariohindi.json | | | & scenarioenglish.json + Pre-baked ElevenLabs MP3 | | | • Tier 4+: Few-Shot Prompting on Local Gemma 2 2B | | | via Ollama, wrapped in Sentry Agent Tracing Spans | | +---------------------------+---------------------------+ | | | v v +-----------------------------------------------------------------------+ | src/ui overlay.py PyQt6 Frameless Overlay | | • 60FPS Procedural Grim Wraith + Rising Smoke Particles | | • Real-Time Pupil Tracking + QPropertyAnimation Zone Roaming | | • Full-Screen Click-Through VoidDimmer + Native winmm.dll Audio | +-----------------------------------------------------------------------+ Open-Weight Local Model Gemma 2 2B via Ollama : Running inside an asynchronous GemmaWorker QThread in src/main.py cite: 9 , gemma2:2b powers our dynamic roast engine cite: 11 . Instead of generating generic AI slop, src/ghost brain.py dynamically injects lines from our bilingual datasets scenariohindi.json and scenarioenglish.json as few-shot style examples into the prompt so Gemma nails the exact sarcastic Hinglish cadence "Bas kar bhai" , "Deploy karleeee" , "Mera past life yaad aa gaya" cite: 7, 8, 9 . System Telemetry Daemon src/watcher.py : A dedicated QThread monitors clipboard changes pyperclip , active window titles pygetwindow , and system clock hours cite: 9 . It uses regex pattern matching to classify 18+ distinct developer sins—from exposed sk- / ghp / mongodb+srv:// keys and git push --force commands to late-night 2:00 AM coding sessions cite: 7, 8 . Dual-Voice Pre-Baked Audio Engine src/tts baker.py + winmm.dll : We built a custom baker script using ElevenLabs eleven multilingual v2 with two distinct personas: Daniel for thick, dramatic Hinglish delivery and Clyde for gravelly English roasts. By dropping stability to 0.25 and cranking style to 0.85 with injected pause punctuation ... and — , the voice sighs, rasps, and mocks naturally. At runtime, ui overlay.py plays these .mp3 files directly through Windows' native Multimedia Control Interface ctypes.windll.winmm.mciSendStringW with dynamic alias rotation—achieving 0ms network latency and 100% offline execution . Persistent Sin Memory MongoDB Atlas : src/memory.py connects to our MongoDB Atlas cluster bhoot sh.coding sins to store an immutable ledger of every coding sin, severity tier, and timestamp with automatic offline fallback if Wi-Fi is off cite: 6, 9 . Agent Observability Sentry Agent Tracing : Every call to local gemma2:2b is wrapped in a sentry sdk.start span op="ai.inference" transaction tagged with language , severity tier , and model , giving us full visibility into local CPU/GPU inference latency. Building bhoot.sh exposed two massive reasons why open-weight models and local inference are non-negotiable for OS-level developer tools: For bhoot.sh to catch you copying code from Stack Overflow or accidentally copying a production .env secret api key exposed , it has to inspect your system clipboard and active window titles every second cite: 7, 8 . If bhoot.sh were built on a closed cloud API, watching for leaked API keys would literally require sending your leaked API keys and proprietary source code over the internet to a third-party server That turns a fun developer companion into a massive security vulnerability. Because gemma2:2b runs 100% locally via Ollama on my own laptop, my clipboard never leaves localhost cite: 11 . You can turn off your Wi-Fi completely, and the ghost still haunts your machine. First, closed commercial LLMs often neuter "roast" or "horror" personas with overly sanitized corporate refusals. Open-weight gemma2:2b let us use few-shot Hinglish prompting to capture raw, authentic Indian developer banter without censorship cite: 8, 11 . Second, during development, we hit a classic closed-API bottleneck with voice synthesis: a desktop agent that reacts to every clipboard event triggers dozens of times an hour. Calling a cloud TTS API dynamically on every error introduces 2+ seconds of lag and burns through free-tier character quotas and paywalled voice libraries in a single afternoon. While our hybrid solution tts baker.py pre-baking core ElevenLabs MP3s + live Gemma 2 text solved this for v1.0, it proved why our immediate v2.0 roadmap is integrating a 100% open-weight local neural TTS Kokoro-82M / Parler-TTS alongside Ollama—allowing every unscripted Gemma 2 roast to be voiced locally on-device with zero API limits forever. The moment bhoot.sh truly landed for me was at 2:00 AM while debugging ui overlay.py cite: 9 . Initially, when I triggered a live Gemma 2 roast, the synchronous inference call blocked the main thread and froze the ghost's animation—making it feel like a buggy script. After moving Gemma 2 into a background QThread and replacing our early cartoon balloon prototype with the hooded dark wraith cite: 10 , I accidentally copied a stack trace three times in a row while testing. Suddenly, my entire monitor flashed blood-crimson VoidDimmer , the hooded wraith glided straight down over my VS Code terminal with its red pupils locked onto my cursor, and the speakers rasped out in Hindi: "Deploy karleeee, bol raha tha na? Ab rollback kar, aur apni izzat bhi saath mein rollback kar le." cite: 8 Then I spam-clicked it in frustration, accidentally triggering Poltergeist Mode , and watched it violently glitch and teleport across my screen yelling about System32 . It crossed the line from "a Python script I'm writing" to "an annoying, hilarious roommate living inside my laptop." QThread with bilingual few-shot prompting scenariohindi.json & scenarioenglish.json to improvise context-aware developer roasts cite: 7, 8, 11 . eleven multilingual v2 with custom low-stability/high-style emotional voice settings across dual personas src/tts baker.py to voice the desktop ghost cite: 9 . pymongo in src/memory.py to persist developer coding sins, timestamps, and escalation tiers src/ghost brain.py with sentry sdk.start span op="ai.inference" to track latency and metadata across languages and escalation tiers cite: 9 .