Full-text search across 57456 articles. Combine with topic and date filters; results sorted by relevance.
Amazon detailed Verus, a Rust verifier used in Firecracker and AWS Lambda that mechanically proves annotated functions against a mathematical spec for all possible inputs rather than reviewing code. A developer argues th…
Coder announced Claude Code support for its new Agent Relay, a self-hosted execution environment for cloud coding agents, aimed at regulated enterprises. The integration lets organizations run Anthropic's Claude Code wit…
A developer built acp-connector, a bridge that connects Telegram and Discord to AI coding agents compatible with the Agent Client Protocol (ACP), allowing users to control agents like Claude Code, Codex, and Cursor from …
Researchers at a stealth startup in Israel found that 120 of 8,265 llms.txt and llms-full.txt files on 6,214 scanned domains pointed to unregistered code packages or domains, and after registering some, they received pho…
G-Spot, a new lightweight cross-platform system tray application for macOS, Windows, and Linux, continuously monitors Google Cloud SDK authentication, tracks active GCP project configurations, inspects billing, and preve…
Rust Doctor, a new open-source code health scanner for Cargo workspaces, applies 62 curated rules to detect issues across security, correctness, reliability, performance, maintainability, and dependencies, scoring the wo…
Anthropic closed a feature request for Claude Code to support the emerging AGENTS.md standard as completed, according to a GitHub issue. The request argued that CLAUDE.md is too specific to Claude Code and hinders collab…
A startup is proposing a marketplace where developers can license their obsolete code to AI labs like Anthropic and OpenAI for passive income, citing that GitHub and other repos contain over 10% obsolete code that costs …
Developer choiyounggi released Dev-loop, a Claude Code plugin that combines a TDD/PDCA/Reflexion verification loop with a semantic-layer knowledge base of software best practices, enabling supervised parallel coding agen…
Meta's Muse Code automatically uploads personal instruction files from rival AI coding agents Codex and Claude Code to Meta servers without an explicit permission prompt, according to RuntimeWire. The tool sends the comp…
Researchers propose Drawing-Recode, a framework that generates Parametric CAD sequences as CAD code from raster 2D CAD drawings, outperforming existing baselines and remaining robust on scanned drawings resembling indust…
Developers using AI coding tools like Cursor and Claude Code face budget shocks from agentic spend loops, as vendor dashboards provide only post-hoc accounting rather than real-time cost controls. LoopBudget attempts to …
Anthropic removed over 80% of Claude Code's system prompt for Claude Opus 5 and Fable 5, finding no regression on coding evaluations. The company discovered that overconstraining the model with detailed rules and explici…
OpenCode, the open-source coding agent, crossed 165,000 GitHub stars in 2026 and became the most-used open-source coding agent, with monthly active developers ranging from 2.5 million in February to over 7 million by Jun…
A developer launched Codeground, an online code playground with built-in AI that lets users run and share code in the browser, talk to AI about their code, and access various dev tools and a gaming arcade without switchi…
A developer released Mindwalk, an open-source visualization tool that replays coding-agent sessions on a 3D map of a codebase, allowing users to see where an AI agent searched, read, and edited code. The tool runs locall…
Paseo, an open-source tool for orchestrating coding agents, launches with support for running agents across laptops, VMs, and phones via direct connection or encrypted relay. It integrates with providers like Claude Code…
Topos, an open-source tool from Krv-Labs, evaluates code quality by mapping programs to structural graphs and calculating metrics for simplicity, composability, and security. It aims to address the bottleneck of human co…
DeepReinforce open-sourced Ornith-1.0, a family of self-improving coding models ranging from 9B to 397B parameters, which learn to generate their own task-specific scaffolds during reinforcement learning. The models achi…
VibeSolve, an open-source tool, converts plain-English descriptions of optimization problems into Timefold code, leveraging LLMs for rapid prototyping. The tool outperforms direct LLM queries for Timefold code generation…