Full-text search across 61882 articles. Combine with topic and date filters; results sorted by relevance.
Enola Labs released enola, a local Model Context Protocol server that builds a deterministic architectural graph of codebases from source code for AI coding agents. The tool extracts precise structural models — modules, …
A developer has outlined a portable AI coding setup designed to work across any tool, including Claude Code, OpenAI's Codex, Cursor, and Windsurf, by relying on open standards rather than vendor-specific configurations. …
Three AI coding tools — OpenAI's Codex CLI, Anthropic's Claude Code, and the Hermes Agent orchestrator — have converged on a shared command format called /goal that lets developers define a "done" state and walk away whi…
A developer built and released Approval Box, an iPhone app that routes approval and decision requests from AI coding agents running on a PC to the user's phone, letting them answer remotely so stalled sessions can resume…
Softwarewrighter published the Flow library in X_eTaL-ML, which lets developers write machine-learning pipelines as left-to-right macros that expand into ordinary right-to-left X_eTaL code. The library's demo builds a tw…
The open-source Reverse Engineer Anything (REA) project connects AI coding agents such as Claude Code and Codex to reverse-engineering tools including Ghidra, Hopper and IDA through MCP servers, letting developers inspec…
Linus Torvalds' new Linux kernel branch credits Claude Code for the code, tests and a draft commit message, while Microsoft's MAI-Code-1.1-Flash runs locally as a 3-bit build with 256K context and free local calls at a r…
AuraPunk is being built as an Agentic Development Environment (ADE) that organizes autonomous coding agents as first-class engineering work, using cards/SPECs to bind intent, execution, and evidence across sessions. The …
Enjoy, a desktop workspace for building software with coding agents such as Claude Code, Codex, Grok Build and Antigravity, launched with a free tier and a $14.99-per-month plan, according to founder Mo. The app runs on …
A software engineer reports that shifting from AI-assisted "vibe coding" to interrogating AI-generated code cut his productivity gain from an assumed 100x to roughly 20% while improving his comprehension of large codebas…
An anonymous engineer argues that AI-driven code generation is the next rung on the same ladder as compilers, high-level languages, and package managers, and that engineers who fear losing the act of typing are confusing…
A software engineer writing in a first-person essay argues that AI coding tools have finally delivered the abstraction layer the industry long sought, letting developers skip dependency hell, setup work, and nitpicky cod…
Superpowers 6.4 adds support for three coding agents — Meta's Muse, OpenCode 2.0 and Qwen Code — and reinvents its Native Execution skill for frontier models, according to the release announcement. The release's evals wi…
Specific Labs released Real-SWE, an enterprise-code SWE benchmark whose leaderboard shows that the same CLI harness can produce more than a 2x score gap depending on the underlying model. Results such as Codex CLI scorin…
Paint.NET creator Rick Brewster announced that the image editor now includes a from-scratch, clean-room reverse-engineered rewrite of Microsoft's Direct2D API, enabling the software to run on WINE/Linux via a new PaintDo…
Meta's Muse Spark 1.2 is now available on Vercel AI Gateway, featuring improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows. The model is designed for long-horizo…
Code review culture has become overly rigid, treating merged code as permanent when it should remain mutable, according to a developer arguing for more trust in experts and cheaper refactoring via coding agents. The auth…
Apple has opened the coreai-models repository, which ships agent skills alongside on-device model export recipes and Swift runtime code, signaling that coding agents are first-class users of its Core AI stack. The repo i…
GitHub has made repository-level Copilot usage metrics generally available via two new REST API endpoints, enabling enterprise and organization users to view daily, per-repository breakdowns of pull request activity for …
Werner Vogels, CTO of AWS, introduced the concept of 'Verification Debt' during his re:Invent 2025 keynote, describing it as the growing gap between the speed of AI-generated code and the capacity for human review. Unlik…