Full-text search across 58829 articles. Combine with topic and date filters; results sorted by relevance.
A developer released an open-source ePub reader that integrates coding agents from GitHub Copilot, Claude Code, Codex, and Gemini, allowing users to chat with an AI agent about the book's content using their existing CLI…
Claude Code, an AI coding assistant from Anthropic, demonstrated the ability to develop native macOS kernel drivers and autonomously resolve support tickets by interacting with service provider AI agents, completing a ti…
AI coding assistants including GitHub Copilot, Cursor, and Claude Code risk selecting dependency versions that are outdated, recently published, or non-existent, according to a new analysis of the tools' behavior.
A developer reports that running multiple coding agents in parallel, such as Claude Code, Codex, and Cursor, introduces a new bottleneck: the delay between when an agent needs human input and when the developer notices. …
A developer recounts being challenged by a senior engineer after relying on AI to generate code without fully understanding the task. The experience highlighted the difference between assembling code and building it, pro…
Developer Dext4r (Zaxs) has released env-guard, an open-source tool that prevents AI coding agents from exposing sensitive credentials like API keys. The tool works by having agents reference secrets by name only, with t…
A developer launched Testmagic.link, a zero-setup email testing service for coding agents, after Claude Code repeatedly used his personal Gmail for magic-link authentication tests. The service requires no signup, API key…
A developer has devised a workflow that uses OpenAI's Codex as a manager to coordinate multiple AI coding agents, including Claude Code, Pi, Copilot, and OpenCode executors. The approach relies on reusable skills and sha…
A developer building Shipsure, a tool for adding visibility to AI-built applications, argues that the hardest part of vibe coding is not building the app but debugging it when it quietly goes wrong in production. The dev…
Fx, a tiny, open-source coding agent harness and CLI written in Zig, has been released as v0.0.3 with a 6.39 MiB binary, designed for minimalism, performance, and embeddability. It cold starts in 10µs, has a minimal memo…
A developer has released StackBridge-MCP, an open-source Model Context Protocol server that tracks cross-boundary contracts in full-stack codebases to prevent AI coding agents from silently breaking frontend code. The to…
Z.ai, the international brand of Chinese AI company Zhipu, launched GLM-5.3, an update focused on coding, long-horizon tasks, and cybersecurity, claiming a 50% higher score than GLM-5.2 on its internal Z.ai Code Bench. T…
A developer reports that their team's rapid adoption of AI-assisted coding has resulted in significant technical debt, making the codebase difficult to navigate and onboard new developers. The team is now considering rew…
Hermenics has released DeepSeek Code, an open-source CLI designed for working with DeepSeek AI models in the terminal. Inspired by Claude Code and OpenAI's Codex, the tool is available via npm and bun, and the project we…
Developer Gregory Terzian released uni03C0, a new macOS client for the headless coding agent pi.dev, designed to address performance, usability, and sandboxing shortcomings in existing coding agent UIs. The client, built…
Lucid, a new output style for Claude Code, reduces jargon and rambling to make responses easier to understand in one pass, lowering the reader's cognitive load. The style keeps coding instructions intact while streamlini…
Waku, a native desktop app built with Rust and GPUI, launched to manage coding agents locally, offering a unified timeline for sessions, transcripts, tool activity, and checkpoints. The app supports multiple agents via n…
Noviz AI has launched open source code for an ERP agent architecture, enabling integration of AI agents with enterprise resource planning systems. The release provides developers with the code and architecture to build a…
A developer building the BitFun coding agent argues that an AI coding agent should not review its own patch due to a conflict of interest, and proposes a structured review loop with a read-only reviewer, bounded evidence…
A developer created Bowls Above, an idle desktop game that rains balls while coding agents like Codex or Claude think, and stops when they yield, aiming to replace doomscrolling during coding waits. The game evolved from…