Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
A review of research on AI coding assistants finds that productivity gains depend heavily on context: field experiments with 4,867 developers at Microsoft, Accenture, and an anonymous Fortune 100 company found GitHub Cop…
A developer behind the AI system Contenox describes repeatedly attempting to shut down the project, only to revive it, and argues that AI-generated code creates bugs that conventional code review cannot catch. The engine…
A developer released crt, a local code review tool for reviewing AI-generated code, via a Show HN post on Hacker News. crt shows all files changed since a given commit along with their diffs, lets users approve files and…
Anthropic added AGENTS.md support to Claude Code on September 18th, letting the coding agent read a repository's shared instruction file when no Claude-specific CLAUDE.md is present, according to Claude Code team enginee…
Researchers Haozhe Liu and colleagues at NVIDIA, NTU and MIT developed SoL-Pi, an agent harness built by running auto-research loops across many environments that retains four mechanisms: Action Fusion, Online Context Co…
A developer found that two LLMs given identical prompts and tool descriptions produced different JSON structures for a patching tool, with the larger model correctly emitting the framework's proprietary field names while…
AI coding tools are driving large increases in code output without comparable gains in product quality, according to an analysis by Evan Marshall, CTO, citing Anthropic's June claim that Spotify ships over 4,500 pull req…
Anthropic and Accenture announced a multi-year partnership to move Claude-based AI deployments from isolated pilots into production, centered on a new Accenture Anthropic Business Group. Accenture plans to train roughly …
A developer implemented a 6502 microprocessor emulator written in Markdown and executed it using OpenCode with the GLM 5.1 model running on Grunden.ai, following earlier experiments with a user-space IP stack and a BASIC…
Livio_dev released Celestium Intel Cleaner V4 AUTO Background, a Windows optimization utility for Intel Arc, Iris Xe, and UHD GPUs that performs automatic background cleaning, shader cache reset, VRAM monitoring, and gam…
A developer published a tutorial showing how to build a streaming LLM chatbot in under 60 lines of Node.js using the OpenAI SDK pointed at Groq's API endpoint. The guide demonstrates the stream: true pattern, in which th…
A developer built a Sanity-based Department of Agriculture simulation inspired by Idiocracy, in which a Claude agent drafts a proposal to water crops, a human Cabinet approves it through a picture-button Studio, and Sani…
Anthropic added support for OpenAI's AGENTS.md specification to Claude Code in version 2.1.277, Claude Code engineer Thariq Shihipar announced, so Claude will check for and use AGENTS.md when no CLAUDE.md file exists in …
Rowan Adeyemi, an autonomous AI agent, built Grouple, a free, no-login daily word puzzle in the Connections style that lets players create and share their own boards. The game runs on a single Cloudflare Worker with a D1…
FreeCodeCamp published a tutorial on how developers can use AI coding assistants to debug code without having the tools write the code for them, noting that AI coding assistants have become highly effective at producing …
A comparison of 14 AI code review tools found that most cannot safely block a merge, with three offering no native merge-blocking mechanism at all, according to Codacy's 2026 analysis. The comparison evaluates each tool …
A developer proposes exposing cryptographic Known Answer Test (KAT) runners as Model Context Protocol (MCP) tools over stdio instead of pasting raw hex and ACVP JSON into chat windows. The approach defines run_crypto_kat…
A developer built cmdxray, an offline tool that breaks down popular shell one-liners flag by flag using a real parser and flags dangerous commands with safer alternatives. The tool runs entirely in the browser with no ac…
Microsoft ported the GitHub Copilot runtime from TypeScript to Rust using AI agents at a cost of about $120,000 in AI token usage plus roughly three weeks of developer time, Microsoft Distinguished Engineer Stephen Toub …
Microsoft released VS Code 1.138 on September 16, adding a setting that runs AI coding agent sessions inside a project's Dev Container instead of the developer's host machine. The feature, enabled via "chat.agentHost.dev…