Developer tools news — AI coding assistants, IDEs, CLI tools, APIs, and productivity tools for software engineers. GitHub Copilot, Cursor, and more.
Shopify is moving its flagship Shop app and other mobile apps from React Native back to native Swift and Kotlin, citing internal AI coding agents that can port features between iOS and Android close to autonomously. The …
A developer built Auterix, an open-source tool that enforces a deterministic four-stage workflow to stop AI coding assistants like Cursor, Claude Code, and GitHub Copilot from drifting off a project's architectural const…
Birkly, an open AI-native content management platform, connects AI assistants to sites through three methods: a personal connector that inherits the logged-in user's role, a service agent with a fixed admin-assigned role…
Microsoft shipped Agent Merge in public preview with VS Code 1.136 on September 2, a feature that runs a repeating supervision loop on open pull requests — answering review comments, fixing failing required CI checks, an…
Knecht, a self-hostable tool for building software factories, has entered beta, its developer announced on Hacker News. Knecht connects to GitHub repos and starts each project in an isolated Docker sandbox generated with…
A developer learning AI/ML engineering documented building linear regression from scratch using NumPy rather than relying on scikit-learn's model.fit(), implementing vectorized arrays for linear algebra and gradient desc…
Local LLMs have improved sharply, with Simon P. Couch, senior software engineer at Posit, reporting that the April Qwen 3.5 and Gemma 4 releases each scored 90% on his agentic coding eval, up from 0% for any MacBook-runn…
Steve Yegge asked on X for recommendations on managing 10 to 20 or more coding agents, drawing 600 replies that surfaced tools like Herdr, cmux, Conductor, and the Claude and Codex desktop apps, plus a wave of homemade s…
A developer has documented the architecture for an AI voice sales agent that lets dealers place product orders through a phone conversation, combining Twilio telephony, the OpenAI Realtime API, and LangGraph for stateful…
A growing share of pull request code is now AI-generated, and it fails differently from human-written code — confidently, syntactically clean, and often plausible-looking even when wrong. GitClear's analysis of over 200 …
A developer outlined a split-architecture approach for turning text prompts into manufacturable printed circuit boards, arguing that large language models should handle component selection and connectivity decisions whil…
OpenAI's SWE-bench evaluation harness relies on unisolated host Docker sockets, according to a bug report filed against the project. The report details errors encountered while running the harness on Docker Desktop with …
Vincent moves agentic task ownership from the terminal into a background daemon that owns task state, workflow execution, agent processes, scheduling, the database, and git worktrees, with the TUI, CLI, and API acting on…
Akuity launched its Agentic Control Plane and MCP Server, products that give AI agents the operational context and permissions to act within software delivery pipelines while enforcing the same governance controls Akuity…
A developer released a Tesla screen-sharing tool that lets users control Anthropic's Claude Code from a Tesla's in-car display, including a screen button to toggle voice mode. The creator, who built the tool after runnin…
A developer has published a role-based guide to building MCP agents, arguing that every useful agent consists of four parts: a model, two or three MCP servers, a system prompt, and a write guardrail. The guide maps speci…
RemObjects will present three talks at EKON 30, held November 23–27 in Düsseldorf, covering Delphi application performance, the architecture of AI agents, and a vision for Pascal in 2030. The AI agent session will detail…
A developer has released Tuim, an open-source terminal IDE written in Zig that embeds Neovim as its editing engine via MessagePack-RPC and the ext_multigrid UI extension. Tuim splits responsibilities between a Zig fronte…
An internal machine learning platform built over eight months saw low adoption because engineers did not trust it, not because of a communication gap, according to a first-person account published by LeadDev. The author …
Brig, a tool from the brig-sh project, runs coding agents inside a microVM sandbox on the user's own machine, starting a session with the command `brig run claude ~/code/demo`. The sandbox boots with no credentials, moun…