5 Skills That Make Your Coding Agent Work Better

I gave a coding agent five skills and one real bug. Here's how each skill changed what the agent did, with the actual output.

LLMs Can Generate Paragraphs. But What If You Just Need a Decision? Meet Jev

Meet Jev, a model designed for decision-making rather than text generation. Learn how its decision types work and how to structure requests and questions to get meaningful results.

From Linear Algebra to OpenCV: Understanding Image Transformations

Learn how fundamental linear algebra concepts like vectors, matrix multiplication, and span power everyday image transformations in OpenCV.

Affordable RAG in Go with Gemini File Search: no vector DB, two calls, one hosted store

Hello, I'm Maneshwar, and I'm building LiveReview — a blast-radius aware AI code review built for your business-critical systems. Star us to help devs discover the project, give it a try, and share your feedback to help improve the product. Every team I have been on has

When Coding with AI, You Get What You Inspect, Not What You Expect

AI coding assistants have made code generation cheap, but correctness has not gotten cheaper at the same rate. This is why inspection, not expectation, decides whether AI-assisted code actually works.

A Headless Browser Without a Rendering Engine, Built for Agents

Puppeteer and Playwright run Chromium's full rendering pipeline on every page load, even though nothing is ever shown. Here is the architecture of a headless browser built without one.

How Does AI Know What's Inside an Image? Meet Vision Language Models

Learn how Vision-Language Models process images and text, and discover what happens behind the scenes when AI understands visual information.

How I Reduced AI Coding Agent Token Waste by 70%

AI coding agents often read more code than necessary. When a developer asks a simple question about a function, the agent searches multiple files, opens entire source files, and fills the context window with irrelevant tokens. Usually, with a bigger codebase, it takes a lot of time to execute, consumes

Teaching Your AI Web Design Some Actual Taste

Let me guess. You opened Claude Code, typed "build me a modern landing page," hit enter, and got back something that technically works but somehow looks like every other site you have ever scrolled. Purple to blue gradients. Inter for everything. Little rounded icon tiles floating above every

Introducing dbctx: Compile PostgreSQL Database into LLM-Friendly Context

dbctx compiles a PostgreSQL database into a compact, queryable context file. AI agents and text-to-SQL systems get only the schema, relationships, and field meaning they need, instead of the entire information_schema.

Your AI Assistant Forgets Everything. Memory Layers Fix That

Your agent forgets everything between sessions, and config files only hold the rules you knew to write down in advance. Here's what a memory layer actually does, and what happened when I wired mem0 into Claude Code and let it run on its own.

How to Create Your Own AI Second Brain with Hermes That Works 24/7

Learn how to create and host your own AI second brain with Hermes that remembers, automates tasks, and works for you 24/7.

cloud

Cloud Computing Is Just npm install for Infrastructure

Every time you pull in a third-party package instead of writing something yourself, you make a trade: you stop owning the internals, but you're still on the hook for how you use it, what it costs you at scale, and what happens the day it breaks in production.

asr

How Real-Time Speech Translation Works: ASR, Segmentation, and Context

Discover how real-time speech translation uses ASR, segmentation, and AI context to deliver fast, accurate translations during live conversations.

google

At Last, I clasp: Escaping the G's Apps Script Copy-Paste Gauntlet

Hello, I'm Maneshwar. I'm building git-lrc, a Micro AI code reviewer that runs on every commit. It is free and source-available on Github. Star git-lrc to help devs discover the project. Do give it a try and share your feedback. Hey. Come sit down. I need

AI

Perfectly Hitting the Wrong Target: The Story of an AI Code Review Benchmark

A first-principles critique of the AI Code Review Bench methodology, arguing that AI code review has split into two distinct problems — human comprehension and machine verification — that no single benchmark can yet capture.

finance

Manage Finance Like a Codebase

As developers, we trust Git with our code, our configs, even our notes, but never our money. Here's what happened when I found a tool that treats your finances exactly like a codebase: plain text, versioned, and diffable

Machine-Learning

Building Neural Networks from Scratch in PyTorch: Learn How Training Actually Works

Learn how neural networks work in PyTorch by building one from scratch.

painlessmesh

How PainlessMesh Turns Your NodeMCU Into a Network That Heals Itself

You've probably built a project where one NodeMCU talks to your laptop over WiFi and thought this is great. But what if we need 10 sensors across a large building? And that's where the issues appear. In this article, we'll discuss what happens after

javascript

What Happens When You Run `npm run dev`

Hello, I'm Maneshwar. I'm building git-lrc, a Micro AI code reviewer that runs on every commit. It is free and source-available on Github. Star git-lrc to help devs discover the project. Do give it a try and share your feedback for improving the project. You'

AI

What's Happening With AI Token Prices, and What It Means for Your Budget

A practical look at why AI token prices can feel both expensive and rapidly cheaper, and how falling inference costs change what customers should expect from AI products.

AI

Does your team use different AI agents? Here’s how to standardize your products.

If your team uses a mix of Cursor, Claude Code, and Copilot, things can get messy fast. In this article, we explain how to set up a system to standardize your products, keep your design system consistent, and ensure every AI agent plays by the exact same rules.

mcp

Everyone’s Talking About MCPs: Learn, Test, and Build Your First MCP Server

Learn what MCPs are, how AI tools interact with them, and how to build and test your own MCP server with a hands-on example.

AI

Understanding AI Code Fast: A 60-Second Habit for Institutional Memory

Why teams using AI-generated code still need lightweight verification, and how a 60-second micro-review habit with git-lrc can build institutional memory without reading every line.