AI coding agents — Page 2

54 stories tagged AI coding agents.

Brick-textured "CLAUDE" and "CODE" letters on dark background with yellow "SubAgents 2.0" banner and red "NEW" label

Claude Code Nested Subagents: Power and Cost Explained

Anthropic's nested subagents let Claude Code spawn agents five levels deep. Here's what that actually means for your workflow—and your token bill.

Man with glasses beside a folder icon showing bidirectional arrows between a red sparkle app and blue coding app labeled…

AI Coding Loops Are Replacing the Prompt—Now What?

Samira Barnes4 months ago

AI. Samira Barnes4 months ago

AI Coding Loops Are Replacing the Prompt—Now What?

Developers are designing autonomous AI loops that merge code without human review. The engineering logic is sound. The accountability framework is nonexistent.

OpenAI Plans to Remake ChatGPT as an AI Super App

Rachel "Rach" Kovacs4 months ago

AI. Rachel "Rach" Kovacs4 months ago

OpenAI Plans to Remake ChatGPT as an AI Super App

OpenAI is reportedly overhauling ChatGPT into a full AI super app with coding agents, automation, and new security features. Here's what's verified and what's still reported.

Man in maroon sweater gesturing while speaking in a home office library setting with "TEST FIRST" text overlay in white and…

Test-Driven Development Tames AI Coding Agents

Alex Volkov4 months ago

AI. Alex Volkov4 months ago

Test-Driven Development Tames AI Coding Agents

Red-green-refactor is a decades-old discipline. Brainqub3 argues it's also the most practical fix for AI coding agents that break things while fixing things.

Two developers collaborate at a desk with GitHub's interface displayed on multiple monitors, bathed in red neon lighting,…

May 2026's Most Popular GitHub Projects, Mapped

Marcus Chen-Ramirez5 months ago

AI. Marcus Chen-Ramirez5 months ago

May 2026's Most Popular GitHub Projects, Mapped

35 GitHub projects topped developer charts in May 2026. Here's what the patterns reveal about where open-source AI tooling is actually heading.

Developer monitoring multiple code screens in a futuristic tech workspace with "35 Trending Open-Source Projects on GitHub"…

35 GitHub Trending Tools Reshaping AI Dev Work

Marcus Chen-Ramirez5 months ago

AI. Marcus Chen-Ramirez5 months ago

35 GitHub Trending Tools Reshaping AI Dev Work

From token-efficient agents to a programming language built for bots, GitHub's latest trending repos expose what developers actually need from AI tooling right now.

Man wearing glasses in front of AI Engineer Europe branding with technical diagrams showing "How It Works" and "Cmd+Ctrl"…

FOMAT: When Your AI Agent Follows You Home

Samira Barnes5 months ago

AI. Samira Barnes5 months ago

FOMAT: When Your AI Agent Follows You Home

Michael Richman's Cmd+Ctrl lets you manage AI coding agents from your phone. The right-to-disconnect questions it raises may matter more than the features.

A developer's screen displaying code and documentation with bold black and blue text overlaid stating "9 ARM SKILLS IS…

9-Arm Skills: AI Agents Need Brakes, Not More Gas

Rachel "Rach" Kovacs5 months ago

AI. Rachel "Rach" Kovacs5 months ago

9-Arm Skills: AI Agents Need Brakes, Not More Gas

A tiny GitHub repo called 9-arm-skills argues AI coding agents need behavioral constraints, not more power. The accountability implications go deeper than the code.

Bold text reading "Code Scaler" in yellow box with 3D cube icon surrounded by four outward-pointing arrows on dark background

Claude Code at Scale: The Harness Is the Product

Yuki Okonkwo5 months ago

AI. Yuki Okonkwo5 months ago

Claude Code at Scale: The Harness Is the Product

Claude Code works fine for small projects. But at scale, the model matters less than the harness around it. Here's what that actually means in practice.

CI/CD pipeline showing failed Linux and Windows checks with one passing PowerShell lint check, displayed on dark terminal…

When Your AI Agent Has Write Access to Production

Rachel "Rach" Kovacs5 months ago

AI. Rachel "Rach" Kovacs5 months ago

When Your AI Agent Has Write Access to Production

A developer built AI agents that autonomously fix CI/CD failures and open pull requests. The security architecture is smarter than most. Here's what it gets right.

A friendly blue robot with headphones works on a laptop against a colorful geometric background, representing coding…

9 Codex Tips Straight From the Team That Built It

Yuki Okonkwo5 months ago

AI. Yuki Okonkwo5 months ago

9 Codex Tips Straight From the Team That Built It

OpenAI's Codex team member Jason Lou published his best practices for using Codex—here's what shifts when someone who built the thing tells you how to use it.

Clone the Repo: What AI Coding Agents Actually Need

Rachel "Rach" Kovacs5 months ago

AI. Rachel "Rach" Kovacs5 months ago

Clone the Repo: What AI Coding Agents Actually Need

Michael Arnaldi's "just clone the repo" technique for AI coding agents has real security implications most developers aren't thinking about. Here's the full picture.

Man in glasses smiling at camera with diagram showing code planning workflow, AI Engineer Europe and Vibe Kanban branding…

The Coding Job Is Now Planning and Review—And Needs New Tools

Yuki Okonkwo6 months ago

AI. Yuki Okonkwo6 months ago

The Coding Job Is Now Planning and Review—And Needs New Tools

Louis Knight-Webb argues software engineering is becoming plan-and-review work as AI coding agents mature. He's shutting down his startup to prove it.

Bold yellow and white text reading "GOODBYE AI SLOP" with "NEW" label and arrow pointing to a dark device interface with a…

Fallow: Cleaning Up After AI Coding Agents

Dev Kapoor6 months ago

AI. Dev Kapoor6 months ago

Fallow: Cleaning Up After AI Coding Agents

Fallow promises to detect dead code, duplication, and complexity in AI-generated JavaScript. But who's actually responsible for code quality?

GitHub's Reliability Crisis: When Your Code Host Loses Your Code

Yuki Okonkwo6 months ago

AI. Yuki Okonkwo6 months ago

GitHub's Reliability Crisis: When Your Code Host Loses Your Code

GitHub's uptime has plummeted to 86% in April 2026, losing pull requests and driving major developers like Mitchell Hashimoto to abandon the platform.

Multica Wants to Turn AI Agents Into Project Managers

Bob Reynolds6 months ago

AI. Bob Reynolds6 months ago

Multica Wants to Turn AI Agents Into Project Managers

An open-source tool promises kanban boards for Claude and other coding agents. But do developers actually want their AI assistants managed like tasks?

Desktop with Command Prompt and browser warning of unsafe site, overlaid with illustration of robotic face with glowing…

What Happens When AI Gets Root Access to Your Computer

Bob Reynolds6 months ago

AI. Bob Reynolds6 months ago

What Happens When AI Gets Root Access to Your Computer

A YouTuber gave an AI agent root access to his Linux system. The results reveal both the promise and the friction of our autonomous software future.

Bold "SHOCKER" header with cyan lightning effects above a Google Jitro app icon and verified badge on white background

Google's Gro Wants to Change How Developers Think About AI

Marcus Chen-Ramirez6 months ago

AI. Marcus Chen-Ramirez6 months ago

Google's Gro Wants to Change How Developers Think About AI

Google's upcoming Gro coding agent shifts from task-based prompts to goal-oriented AI. What happens when you stop telling AI what to do and start telling it what to achieve?

Bold yellow and white title with a pixel art character and checkmark icons flanking it against a dark background

AI Coding Agents Need Structure, Not Just Speed

Marcus Chen-Ramirez6 months ago

AI. Marcus Chen-Ramirez6 months ago

AI Coding Agents Need Structure, Not Just Speed

Claude Code can accelerate development, but without proper setup—PRDs, constraints, testing frameworks—AI-generated apps fail at scale. Here's the infrastructure.

Man pointing at a recycling bin with document files labeled AGENTS.md and CLAUDE.md floating above it in a futuristic tech…

AI Context Files May Hurt More Than Help, Research Shows

Samira Barnes7 months ago

AI. Samira Barnes7 months ago

AI Context Files May Hurt More Than Help, Research Shows

New research suggests automatically generated CLAUDE.md and AGENTS.md files decrease AI coding performance while increasing costs by 20%. What developers should do instead.