Recruiters Want Proof of Work on GitHub

Every time I opened a pull request, I felt it. That awkward wait for feedback. What if the first round of review didn't have to wait at all? That question became my MEng Capstone at the University of Cincinnati. My inspiration was simple: combine the AI with traditional web development to solve a real developer pain point. So I built an AI-Powered Pull Request Reviewer, a GitHub App that automatically analyzes code the moment a PR is opened and posts intelligent feedback directly in the thread. And I did it entirely with free resources, even for deployment: React frontend on GitHub Pages FastAPI backend on Render MongoDB free tier for storage 4 AI providers (Hugging Face, Groq, OpenRouter, SambaNova) via free inference APIs, and the architecture is flexible enough to plug in many more! Biggest lesson? Real engineering happens when you work within real-world constraints and still ship something end-to-end. 🔗 Frontend (Live): https://lnkd.in/gkGF-PWE 🔗 Frontend Code: https://lnkd.in/ggJyY-Bc 🔗 Backend (Live): https://lnkd.in/gYHUkmwX 🔗 Backend Code: https://lnkd.in/guRag2ht 🔗 GitHub App: https://lnkd.in/gVZFYcWN #AI #SoftwareEngineering #GitHub #CodeReview #FastAPI #React #CapstoneProject #UniversityOfCincinnati #BuildingInPublic #Opensource #CICD

A stranger-than-fiction turn of events: Anthropic’s accidental publication of a source map in an npm package exposed 2,300 TypeScript files and over 500k lines of code, revealing Claude Code’s internal agents, prompts, and security design. Rather than transparently addressing the leak, Anthropic issued mass takedowns—removing some 8,100 GitHub repos—which sparked developer backlash. In response, open-source contributors (notably Sigrid Jin) performed a clean-room rewrite: reimplementing the functionality from scratch in languages like Python and Rust. The result—Claw-Code—became the fastest-growing project in GitHub history, gaining 50k stars in just two hours. The episode shows how attempts at centralized control can backfire, turning proprietary ideas into resilient, community-owned open-source projects. A reminder: transparency, developer trust, and thoughtful incident response matter—because once an idea is public, communities can—and will—make it unstoppable. #Technology #AI #Programming #GitHub #OpenSource #AI_Agents

Ever stared at a massive GitHub repository and wished you could just ask it how it works? I’ve been diving deep into local AI orchestration and wanted a better way to navigate new codebases. So, I built GitChat, A Retrieval-Augmented Generation (RAG) assistant that lets you chat directly with any public GitHub repository. It dynamically clones a repo, chunks the architecture, and streams context-aware answers back to a sleek, minimalist dark-mode interface. The best part? The LLM inference runs entirely locally. Features: - Dynamic Repo Ingestion: Automatically clones, filters out heavy/binary files, and chunks code for AI ingestion. - Zero-Hallucination Guardrails: Strict prompt engineering ensures the AI only answers using the provided codebase context. - Local LLM Orchestration: Runs models (like Qwen 2.5 Coder) locally, meaning zero API costs for inference. - Real-Time Streaming UI: Seamless, non-blocking message streaming with syntax-highlighted markdown rendering. - Dynamic Sandbox Controls: Real-time adjustments for LLM Temperature, K-value context retrieval, and model selection. The Tech Stack: - Frontend & API: Next.js (App Router), Tailwind CSS - AI Engine: Vercel AI SDK v6, LangChain - Database & Vector Search: MongoDB Atlas Vector Search - Local Models: Ollama (qwen2.5-coder, nomic-embed-text) I'm really proud of the resource management and the seamless integration between the backend data pipeline and the frontend UI. GitChat is fully open-source, and I am actively welcoming contributions! I would love for you to check out the architecture, test it out, or even open a PR if you have ideas for new features. Repository & Code: https://lnkd.in/dNuBfnzZ #Nextjs #LangChain #Ollama #MongoDB #SoftwareEngineering #AI #WebDevelopment

The wall didn't just crack. It vaporized. 🦞 Yesterday, Anthropic accidentally dropped a 60MB source map via npm, exposing 512,000 lines of proprietary TypeScript. But the leak isn't the real story. The velocity is. Enter Claw Code. Within hours, a decentralized swarm used AI to ingest, reverse-engineer, and completely rewrite the architecture into Python. It hit 50,000 GitHub stars in 120 minutes—shattering records to become the fastest-growing repository in the history of the internet. By the time the original developers were pouring their morning coffee, a Rust port was already in motion. We are operating at the pure speed of thought. This is the recursive endgame: we are using AI to dissect the AI that was built to help us write code, translating it seamlessly across paradigms. The Ouroboros is fully realized, and it's executing at runtime. But the deeper philosophical shift here goes far beyond open-source drama. We are witnessing the death of the monolithic software trap. For decades, the industry standard was backward: you bought a piece of rigid, proprietary software and contorted your entire daily workflow to fit its limitations. You compromised your efficiency for the sake of the tool. No more. The new era is fluid. The lesson of Claw Code is that you no longer warp your process to fit the software. Instead, you spawn custom, hyper-efficient software designed entirely to accelerate your process. If a tool doesn't serve you perfectly, you don't adapt to it—you (or a community, powered by LLMs) simply rebuild it from the ground up by lunchtime. (Production grade may need another couple of hours, and you do proper testing) When an entire enterprise product can be ported, localized, and optimized into a bespoke engine in a single morning, proprietary walls aren't just obsolete. They're an illusion. #SpeedOfThought #ProcessFirst #OpenSource #ClawCode #SoftwareEngineering #AIAcceleration #TechPhilosophy #Bi3Technology

🚀 Built an AI-Powered Software Debugger for Developers I’ve been working on a project that turns any public GitHub repo into an intelligent, searchable, and debuggable system in seconds. 🔍 Just provide a repo URL, and the app can: • Generate complete architecture overview • Detect bugs in the code • Create test cases automatically • Generate clean documentation • Search across the entire repository intelligently ⚙️ Tech Stack: Groq + LangGraph + FastAPI + React This project is focused on saving developer time and improving code understanding — especially when working with large or unfamiliar codebases. Would love your feedback and thoughts 🙌 #AI #SoftwareEngineering #React #FastAPI #LLM #DeveloperTools #OpenSource #Innovation Project Link: https://lnkd.in/gExW7MrJ

I just built an AI-powered code review bot from scratch — and it works autonomously on real GitHub Pull Requests. 🤖 Here's what it does: Every time a PR is opened, the bot automatically triggers, reads the code changes, and posts a structured review as a comment — covering bugs, security vulnerabilities, code quality issues, and performance improvements. No human needed. Zero manual work. Here's how it works under the hood: GitHub Actions listens for every new PR The diff is fetched using the GitHub API The diff is sent to LLaMA 3.3 70B (via Groq API) for review The AI's feedback is posted back as a PR comment automatically The whole pipeline runs on GitHub's servers — fully autonomous. What I learned building this: → How to integrate LLMs into real developer workflows, not just chatbots → GitHub Actions and CI/CD pipeline setup from scratch → Working with REST APIs (GitHub + Groq) end to end → How to handle auth, secrets, and permissions in production environments → Debugging live systems — nothing teaches you faster than a 403 error at midnight 😅 This is the kind of tool that saves hours every week for dev teams — and I built it in Python over a weekend. If you're a startup struggling with slow code reviews or want to see this in action — let's talk. 🔗 GitHub: https://lnkd.in/e9T84Xn3 🌐 Portfolio: aaradhya1807.github.io #Python #AI #GitHub #Automation #OpenToWork #MachineLearning #DevTools #LLM

🚨 Every Claude Code developer is panicking right now. And honestly, they should be. Because the people who found these GitHub repos are building 10x faster than everyone else. And you’re probably not one of them. Here are the 5 repositories you need right now: https://lnkd.in/gkGajWhk https://lnkd.in/g9HDS32J

We're making open source… human. Most developers want to contribute. But they get lost in 50,000 Lines of Code, Zero Context So we built PRactice. Pick a real issue from top repos React, Tensorflow, VS Code and more. We break it down in simple terms: what's broken, why it matters. Talk to the AI maintainer about your approach. Fix the Codebase. Submit your fix. Get scored. Get better. 50 spots. Real repos. Zero confusion. Join the waitlist → https://www.practice.rocks This isn't a tutorial. It's how you should've learned from day one. #OpenSource #SoftwareEngineering #OpenSourceContribution #GitHub #100DaysOfCode #LearnToCode #DeveloperTools #WebDevelopment #React #TensorFlow #VSCode #CodingCommunity #TechStartup #ProductLaunch #AITools

𝗠𝗲𝗲𝘁 𝗚𝗶𝘁𝗡𝗲𝘅𝘂𝘀: 𝗔𝗻 𝗢𝗽𝗲𝗻-𝗦𝗼𝘂𝗿𝗰𝗲 𝗠𝗖𝗣-𝗡𝗮𝘁𝗶𝘃𝗲 𝗞𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝗚𝗿𝗮𝗽𝗵 𝗘𝗻𝗴𝗶𝗻𝗲 𝗧𝗵𝗮𝘁 𝗚𝗶𝘃𝗲𝘀 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 𝗮𝗻𝗱 𝗖𝘂𝗿𝘀𝗼𝗿 𝗙𝘂𝗹𝗹 𝗖𝗼𝗱𝗲𝗯𝗮𝘀𝗲 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗮𝗹 𝗔𝘄𝗮𝗿𝗲𝗻𝗲𝘀𝘀 Abhigyan Patwari's GitNexus has quietly crossed 19,000 GitHub stars by solving a problem every AI-assisted developer has hit but rarely named — agents that edit code they don't actually understand. The post Meet GitNexus: An Open-Source MCP-Native Knowledge Graph Engine That Gives Claude Code and Cursor Full Codebase Structural Awareness appeared first on MarkTechPost. https://lnkd.in/euA3X7eF

Ever merged the wrong PR into your GitHub repo? 😅 I’ve done it… and it’s painful. That’s why I built Aivana - an AI powered GitHub PRs reviewer that catches bugs, leaks, and risky changes before you hit merge. Now No more last-minute surprises. No more broken builds. What it does:  - Connects to your GitHub repos via OAuth  - Analyzes every PR diff using Google's Gemini AI  - Flags bugs, security issues, performance problems, and code smells  - Gives each PR a risk score (0-100) so you know what needs attention first     - Shows feedback right alongside your code changes in a visual diff viewer    The tech stack: Next.js 16, TypeScript, tRPC, Prisma, PostgreSQL, Better Auth, Inngest for background jobs, and shadcn/ui for the UI. Built it end-to-end with type safety in mind. Why I made this: I've lost count of how many times I've merged something I shouldn't have. Aivana  is my attempt at making sure that number stops growing. It's not about replacing human review it's about having a second pair of eyes that never gets  tired. Still iterating on it, but pretty happy with how the risk scoring and structured  feedback turned out. The AI catches stuff I'd normally skip over. If you're curious or want to check it out, Give it a try : https://lnkd.in/dHmdmpGb If you want to contribute visit : https://lnkd.in/dHb_ghyd (don't forget to give it a star ⭐) #GitHub #CodeReview #AI #NextJS #TypeScript #DeveloperTools #OpenSource