This week I worked on adding DVC (Data Version Control) to my ML project as part of my MLOps learning journey. Until now, my workflow was simple: train a model and save model.pkl. With DVC, I started thinking more like an MLOps engineer: tracked data/data.csv with DVC instead of Git created a reproducible pipeline using dvc.yaml moved training settings into params.yaml logged model accuracy into metrics.json configured a local DVC remote for storing tracked artifacts What I understood clearly this week: Git is great for code, but not for large datasets DVC helps version datasets, models, and pipeline outputs dvc.yaml makes the training workflow reproducible dvc repro reruns only when dependencies or parameters change One practical lesson from this setup: my environment was WSL-based, so I had to make sure DVC commands and the training pipeline used the correct interpreter from ml-env. That debugging step helped me understand how important environment consistency is in MLOps. This project is part of my plan to build one ML project and improve it week by week instead of creating disconnected mini-projects. Next step: integrating DVC with Dagshub for remote storage, versioning, and collaboration. I’ve documented the project and my DVC notes here: GitHub: https://lnkd.in/g5iMMPvX DVC Notes: https://lnkd.in/gPvcnV88 #MLOps #DVC #Dagshub #MachineLearning #DataVersionControl #Python #LearningInPublic #MLEngineering

Tired of writing commit messages? I built a tool that does it for you.   Introducing git-ai — an AI-powered CLI that lives inside your Git workflow.   What it does:   - Generates commit messages that match YOUR style (learns from your last 20 commits)   - Creates PR descriptions with one command   - AI code review with severity ratings   - Auto-generates changelogs in Keep a Changelog format   - Detects ticket IDs (JIRA, Linear, GitHub) from branch names   - Works with Claude, GPT, Gemini, or fully local with Ollama   Just run:   npm install -g @malikasadjaved/git-ai   git-ai setup   git-ai commit   Three commands. Zero friction. Never write a commit message again.   🌐 Website: https://lnkd.in/dzydYtAj   💻 GitHub: https://lnkd.in/dfEJGaBX   🔗 Connect: https://lnkd.in/dv_dkDsd   Built with frustration from writing commit messages manually. Open source & MIT licensed.   #OpenSource #DeveloperTools #AI #Git #CLI #NodeJS #TypeScript #Programming #SoftwareEngineering

GitHub just shipped an embedding model update that actually matters. Their new Copilot embedding model for VS Code isn't just incrementally better — it's 37.6% more accurate at finding the right code context, runs twice as fast, and uses 8x less memory for indexing. For C# and Java devs, acceptance rates for suggestions have doubled. That's not a feature update. That's a productivity shift. What's interesting: they used contrastive learning techniques (InfoNCE loss + Matryoshka Representation Learning) to train this. The model now powers chat, agent, edit, and ask modes — so the improvements cascade across every interaction you have with Copilot. But here's what I'm thinking about: we're moving from "AI suggests code" to "AI understands your codebase architecture." Better embeddings mean better context retrieval. Better context means suggestions that feel less like autocomplete and more like pair programming with someone who's read your entire repo. For QA folks and builders working in complex codebases, this changes test automation workflows and API integration work significantly. Question: Are you seeing improved Copilot suggestions in your stack after this update, or is acceptance rate still a coin flip for you? #GitHubCopilot #AICoding #DeveloperProductivity #CodeEmbeddings #DevTools

#VSCode + #GitHub + #AI, i am not sure if there is a better way to code nowadays. From static to complex python code. Let’s be honest. If you’re still writing code in 2026 using a basic text editor, you are missing out valuable features. The integration of VS Code with GitHub and the power of AI (#Copilot, #Claude, #Cursor) isn’t just a cool setup. It lets you do things you wouldn't know you can. And with hundreds of extensions available, you can practically develop almost anything from scratch. ✅️ Make commits, pushes, and PRs without ever leaving your environment. Everything happens "in-house." ✅️ With AI you save you 80% of the "boring" work. Boilerplate code? Unit tests? Documentation? You name it. ✅️ With GitHub Codespaces, your environment is everywhere, ready and pre-configured. What you gain? Easy. ➡️ You write code 2x, 3x faster ➡️ Fewer Bugs with AI suggesting code while you write ➡️And the most important, your Mental Health. Instead of wrestling with syntax, you wrestle with logic. #Artificial_Intelligence #Hey_Eye_Facts

I spent a few weekends playing around with Claude Code and Codex, and ended up with something I've actually kept using. The problem was simple enough: my commit messages are terrible. Not catastrophically so, but not the kind of clean, conventional history that's useful six months later. I kept telling myself I'd tidy them before opening a PR. I never did. So I built aic - a Rust CLI that reads your staged diff and generates a conventional commit message. I'm not a Rust developer by trade (infrastructure and DevOps is more my world), but tools like Claude Code makes it surprisingly practical to build and maintain something in a language you'd normally avoid. There's an obvious meta quality to using an AI coding assistant to build an AI-powered git tool too. It's grown a bit since the first working version - it'll now review your staged diff before you commit, draft PR descriptions, rewrite a scrappy local history before you push, split a mixed staged change set into separate commits, and generate SVG visualisations of your repo structure and commit history. Seven AI providers supported, including local ones via Ollama, Claude Code, and Codex. The binary is called aic. Yes, that's an Alice In Chains reference 🎸 Read more at https://lnkd.in/ectdATGC #Rust #Git #AI #DevTools #OpenSource #WeekendProject

You don't need to be a developer to use Claude Code. You need to know what problem you're solving. I've seen this confusion a lot lately: Claude Code gets covered as a "developer tool." People assume it requires knowing Python, Git, or terminal commands. Here's the reality: Claude Code is a thinking partner that works in your file system. If you can describe a business problem clearly, Claude Code can help you build the solution — even if you've never written a for loop. What non-technical operators actually use it for: → Automating their content research (like what generated this post) → Building client-facing reports from raw data → Creating internal playbooks that update themselves → Stringing together tools that weren't designed to talk to each other The missing piece isn't technical skill. It's learning to think in systems. The operators who win with AI aren't the ones who code. They're the ones who can describe outcomes clearly. Claude Code just makes that description executable. Are you using Claude Code in your business? What's your use case? #ClaudeCode #AIForOperators #AIAutomation #BusinessAutomation #NoCode

Developers are constantly seeking ways to streamline their workflows and make the most of their time. In the realm of LLM and agent workflows, teams often struggle to balance reliability and power. Most rely on cumbersome server-side solutions that are difficult to scale and maintain. This is where ComposioHQ/awesome-codex-skills comes in – a curated list of practical Codex skills for automating workflows across the Codex CLI and API. At its core, this repository provides a collection of Python-based skills that can be used to improve the reliability and efficiency of agent behavior. What stands out is the variety of skills available, including bernstein – a multi-agent orchestrator with Codex CLI adapter, and what Are Codex Skills? – a fundamental question that gets to the heart of how these skills work. What makes this repository particularly interesting is how it addresses a common pain point in the development process. By providing a list of practical skills that can be easily integrated into existing workflows, ComposioHQ/awesome-codex-skills makes it easier for developers to make agent behavior more reliable, not just more powerful. Here are some key highlights: - bernstein – Multi-agent orchestrator with Codex CLI adapter. Runs parallel Codex agents in isolated git worktrees with quality gates. - what Are Codex Skills? - a curated list of practical Codex skills for automating workflows across the Codex CLI and API. - built with Python The traction makes sense: a repository sitting at #3 with around 637 new stars in the current trending window is usually solving a problem people can feel immediately. With its focus on making fast-moving AI workflows easier to steer and reuse in real projects, it's no wonder that ComposioHQ/awesome-codex-skills is getting attention. Repo: https://lnkd.in/eTmpF-UT #GitHub #OpenSource #GitHubTrending #LinkedInForDevelopers #Python #AwesomeCodexSkills #Awesome #AwesomeLists

🧠 What a project's git history reveals — without reading a single line of code I took an open source repo I had never seen before: RAG-Anything (HKUDS, 1k+ stars on GitHub). 333 commits. Zero code reading. Just git metadata. Here's what emerged in seconds 👇 (see screenshot picture) A senior developer joining this project cold would spend hours mapping this coupling. This took 12 seconds. No LLM calls. Pure graph inference. Here's the insight behind this: The architecture of a project is not in the code. It's in the co-modification patterns — which files evolve together, in which order, how often. Every git commit is a signal. Accumulated over months, those signals reveal something no static analysis tool can see: how the project actually thinks. Current AI coding agents forget everything between sessions. They rediscover your project every single time. What if your agent remembered — not just your code, but the architectural soul of your project? That's what we're building. 🚧 👉 Repo used for this demo: https://lnkd.in/dfkVb_Kt #AI #DevTools #SoftwareEngineering #BuildInPublic #AgentAI

🚨 #50K #stars 💫💫💫 in #2HOURS and still counting. 🤯🤯 with currently #100K forked on GitHub #SameDay Not days. Not weeks. #Two. #Hours. 👉 #ClawCode : https://lnkd.in/g_3-3Zf2 And yes… I already forked it the moment it dropped.😀😀😀😊😊😊 At first, people thought it was just: 👉 a leaked version of Anthropic #ClaudeCode But what happened next is what really matters… 💥 The creator (behind #instructkr) didn’t just post it— he turned it into something usable almost immediately And then… ⚡ started porting it to Python in #ONE #night. Then, release to #Rust in #ONE #day 🦀 That’s when it clicked for me: 🤯This is not a leak anymore. This is becoming a real system. 🧠 What makes this repo different? ❤️🔥It’s not about prompts. ❤️🔥It’s not about chat. ❤️🔥It’s about a true agent harness: ➡️ Plan ➡️ Generate ➡️ Execute ➡️ Observe ➡️ Fix ➡️ Repeat 👉 It doesn’t stop at an answer 👉 It keeps going until the task actually works 🔥 After playing with it a bit, my biggest takeaway: The #magic is NOT the #model. It’s the loop + execution + feedback design ⚙️ This could go even bigger 🤯 than OpenClaw. → real execution → self-correcting system → end-to-end task completion 👉 It feels like the early version of a self-operating engineer 📰 Even The Wall Street Journal is covering the rise of “vibe coding” tools (#ClaudeCode, #Cursor, #Codex …) But this feels like the next step: 💡 Not “AI helping you code” 💡 But AI owning the entire coding loop 📊 My takeaway (after forking + testing day 1): We’re entering a new phase: 💫Model = brain 💫Harness = system 💫Loop = intelligence And honestly… 👉 This might be the moment where software design starts mattering more than model size ⚡ 50K stars in 2 hours isn’t just viral. It’s the community saying: 👉 “THIS is the direction.” #AI #Agents #LLM #OpenSource #Python #Rust #VibeCoding #FutureOfWork #Opensource #ClaudeCode

There’s been a lot of discussion lately around the unexpected exposure of Anthropic’s Claude Code—and beyond the headlines, there are some genuinely interesting takeaways for engineers and builders. First, what happened? The leak appears to have been accidental, with source code exposed through a map file on an npm registry. While takedowns may follow, the reality is that parts of the code have already been reimplemented elsewhere (e.g., in Python), which makes containment difficult. But the real value is in the insights it revealed. This incident gave us a rare look into how a modern coding agent is actually designed and operated at scale: Configuration-driven behavior (Claude.md): A central file that gets loaded every turn, allowing teams to enforce coding standards, architecture decisions, and best practices consistently. This is a powerful pattern for maintaining alignment across AI-assisted development. Parallel execution as a first-class concept: Instead of a single-threaded agent, Claude Code leverages multiple sub-agents working in parallel (e.g., via Git worktrees), enabling faster and conflict-free development workflows. Smarter permission handling: The “auto” mode uses an LLM-based classifier to decide which actions are safe—reducing friction from constant prompts while still maintaining a level of control. Context management (compaction): One of the hardest problems in LLM systems—managing context—is handled via a “/compact” approach, effectively letting the system decide what to retain and what to forget, similar to saving state in a game. Persistent sessions: Instead of starting from scratch every time, sessions can be resumed with full context and history intact. This significantly improves productivity and continuity. Hooks for extensibility: Advanced users can plug into different lifecycle events (like pre-tool usage or session boundaries) to automate workflows—for example, updating documentation after commits. Operationally, there are also some practical lessons: Interrupt early when things go off track—streaming makes it cheap. Separate read-only and mutating operations to enable better task delegation and parallelism. Final thought: While leaks are never ideal, this one has unintentionally accelerated learning across the developer ecosystem. It reinforces an important idea: the future of engineering isn’t just about using AI tools—it’s about designing systems around them. Curious to hear how others are thinking about building AI-native development workflows. #claude_code #ai #github #leak #claude_code_leak