How to Write Prompts When You’re Vibe Coding
Cursor and ChatGPT already changed how I work A few years ago, coding felt like a solo sport: you, the keyboard, and Stack Overflow when things went s…
Open Source
⚑ Report a ProblemLatest Open Source news from Tech News
All topics
AI
agents
ai
api
architecture
automation
aws
beginners
career
claude
database
devchallenge
devops
discuss
javascript
linux
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
rust
security
showdev
tutorial
typescript
webdev
Agentic Coding with Cursor
Cursor is an AI-assisted IDE with AI features baked-in, such as agent-based coding assistance, predictive autocomplete, and MCP support. It is a fork …
10 фичей Claude Code, которые превратили одного разработчика в команду из 15 человек
512 000 строк утёкшего кода, совещание ботиков, и почему человек стал узким местом разработки 31 марта 2026 года Anthropic случайно выложила npm-пакет…
MCPNest Gateway — One URL to Rule All Your MCP Servers
MCPNest v1.11 | April 2026 The MCP ecosystem has a governance problem. Developers are installing MCP servers directly into Claude Desktop and Cursor —…
How to Use Next.js Templates with Cursor and Claude Code (2026 Workflow)
If you bought a Next.js template in 2023, you spent a weekend customizing it. If you buy one in 2026, you spend an afternoon — if you use AI coding to…
Stop picking Cursor or Claude Code. Pay for both, you cheapskate.
Each week I see a new post asking "Cursor vs Claude Code — which do you choose?" And each week I keep on scrolling. The comparison is false, and deep …
Вайбдебаггинг — уже реальность? Мы дали ИИ-агенту отладчик и проверили
В конце прошлого года Cursor выпустил Debug Mode — режим, в котором агент может собирать логи из рантайма, чтобы лучше понимать причины багов. Судя по…
Тестируем Yandex Code Assistant на задаче, в которой нужно хранить секреты
Всем привет! Меня зовут Станислав Денисов, я ML-инженер в компании «Инфосистемы Джет». Из-за вайбкодинга Хабр пережил уже не один холивар и переживет …
The agent over-applies everything: why “don’t” is my most-used word
Models: Opus 4.6, Sonnet 4.6, Composer 1.5, Composer 2 In 60% of my agent sessions, I had to correct the output. The single most common word in those …
kasetto - declarative AI agent environment manager, written in Rust
https://www.kasetto.dev https://github.com/pivoshenko/kasetto Hey DEV community! 👋 I want to share an open-source tool I built for myself, and that I …
A 13MB Cursor Monitor: AppKit, Undocumented APIs, Zero Dependencies
My company recently started supporting Cursor, so I jumped in. But checking usage meant opening the dashboard every time — and if Max mode was on with…