The latest articles on DEV Community by akshvy (@akshvy). https://dev.to/akshvy https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F1962469%2F95fd5602-b029-48d4-9b5f-161e07fde90d.jpeg https://dev.to/akshvy en akshvy Sat, 10 Oct 2026 17:47:57 +0000 https://dev.to/akshvy/linguagrass-ngi https://dev.to/akshvy/linguagrass-ngi <p><em>This is a submission for the <a href="https://dev.to/challenges/hacktoberfest-week1-2026-10-05">Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass</a></em></p> <h2> What I Built </h2> <p>I built <strong>LinguaGrass</strong>, a translator that you use without looking at a screen. You wear a mic and an earphone, keep your laptop in your bag, and when someone speaks Hindi to you, you hear the English in your ear a few seconds later.</p> <p>I made it because translation apps make you stare at your phone right when you should be looking at the person talking to you. This way you keep eye contact and actually enjoy where you are. It's for travelers, backpackers, and anyone who has been stuck in a market with no common language.</p> <h2> Code </h2> <div class="ltag-github-readme-tag"> <div class="readme-overview"> <h2> <img src="https://assets.dev.to/assets/github-logo-5a155e1f9a670af7944dd5e12375bc76ed542ea80224905ecaf878b9157cdefc.svg" alt="GitHub logo"> <a href="https://github.com/akshvy" rel="noopener noreferrer"> akshvy </a> / <a href="https://github.com/akshvy/linguagrass" rel="noopener noreferrer"> linguagrass </a> </h2> <h3> LinguaGrass is a screenless, eyes-free real-time translation system designed for travelers, backpackers, and cross-cultural explorers. </h3> </div> <div class="ltag-github-body"> <div id="readme" class="md"><div class="markdown-heading"> <h1 class="heading-element">linguagrass</h1> </div> <p>LinguaGrass is a screenless, eyes-free real-time translation system designed for travelers, backpackers, and cross-cultural explorers.</p> </div> </div> <br> <div class="gh-btn-container"><a class="gh-btn" href="https://github.com/akshvy/linguagrass" rel="noopener noreferrer">View on GitHub</a></div> <br> </div> <br> <h2> How I Built It </h2> <p>It's a simple pipeline in Python:</p> <p>Mic → faster-whisper → Qwen 2.5 3B (Ollama) → ElevenLabs / Piper → Earphone</p> <ul> <li> <strong>faster-whisper</strong> listens and turns speech into text, locally.</li> <li> <strong>Qwen 2.5 3B</strong> (open-weight, running through Ollama) translates it, also locally.</li> <li> <strong>ElevenLabs</strong> speaks the translation when there's internet. If there's no signal, it switches to <strong>Piper</strong>, an open-source offline voice.</li> </ul> <p>Right now it only does Hindi to English, and I tested it with everyday sentences like asking for directions or prices. It takes about few seconds per sentence on my laptop. [ONE REAL LIMITATION YOU NOTICED].</p> <h2> Why Does Open Innovation Matter? </h2> <p>Places where you need a translator most, like trails and village markets, often have no signal. Because Whisper and Qwen are open models, the main part of the project runs on my laptop with the internet off. A closed cloud API simply wouldn't work there.</p> <p>It also keeps other people's voices on my device instead of sending them to someone's server, and it costs nothing to keep running.</p> <h2> Prize Categories </h2> <ul> <li>Touch Grass (main theme)</li> <li>ElevenLabs</li> </ul> devchallenge hf26challenge akshvy Fri, 02 Oct 2026 06:24:25 +0000 https://dev.to/akshvy/placementbuddy-cli-local-c-ai-placement-assistant-for-my-classmate-5ja https://dev.to/akshvy/placementbuddy-cli-local-c-ai-placement-assistant-for-my-classmate-5ja <p><em>This is a submission for the <a href="https://dev.to/challenges/hacktoberfest-weekend-2026-10-01">Hacktoberfest Weekend Challenge: Build for a Friend</a></em></p> <h2> What I Built &amp; Who It's For </h2> <p>I built <strong>PlacementBuddy CLI</strong> for my college friends preparing for campus placement drives and technical DSA interviews. </p> <p>Reviewing code with web AI tools means constant context switching, rate limits, and privacy concerns. <strong>PlacementBuddy CLI</strong> runs <strong>100% locally</strong> in the terminal using native C++17 and Ollama—giving classmates instant complexity analysis, edge-case checks, and practice questions with <strong>zero API costs</strong> and <strong>zero data leaks</strong>.</p> <h2> Why Native C++ &amp; Local Open-Source AI? </h2> <ul> <li> <strong>Native Speed:</strong> Built with C++17, <code>libcurl</code>, and <code>nlohmann/json</code> for minimal memory overhead and zero runtime lag.</li> <li> <strong>100% Private:</strong> Code and interview notes stay on the local machine (<code>http://localhost:11434</code>).</li> <li> <strong>Offline Execution:</strong> Once the model (<code>llama3.2</code> / <code>gemma</code>) is pulled, no active internet connection is required.</li> </ul> <h2> How It Works </h2> <div class="highlight js-code-highlight"> <pre class="highlight plaintext"><code>C++ Source File / Notes (.cpp / .txt) │ ▼ [ placement_buddy ] ──&gt; Parses args (dsa | quiz | explain) &amp; constructs payload │ ▼ [ libcurl Stream ] ──&gt; Sends async HTTP request to local Ollama daemon │ ▼ [ Terminal Output ] ──&gt; Streams colorized ANSI response line-by-line in real time </code></pre> </div> <p>📁 Repository: github.com/akshvy/placement-buddy-cpp</p> hf26challenge devchallenge weekendchallenge cpp