All articles tagged with #developer tools
Google unveils a dedicated Googlebook developer hub that guides developers to build desktop-grade apps using multi-pane layouts, precise input handling, contextual cursors, and true multi-window and drag-and-drop support, with Android Studio Canary's desktop emulator and Adaptive AI Skills to auto-generate desktop-optimized layouts ahead of a fall rollout.
Roku has begun a staged rollout of Roku OS 15.2 to compatible TVs and streaming players. The update focuses on developer-facing improvements—Perfetto-based app tracing with a BrightScript heap graph, the chanperf command for raw CPU stats, new debug protocol variables, and expanded BrightScript APIs for low-memory handling and input control—along with AES-GCM encryption support. End users should see smoother performance, faster app launches, more reliable playback, and better multitasking as the rollout continues over several weeks to a month, with some older devices likely receiving fewer features or updates on a different schedule.
OpenAI today launched Codex for Chrome, a Chrome extension that lets Codex run directly in the browser on Macs and PCs, enabling it to test web apps, share context across tabs, use DevTools, and more without taking over the browser; the extension is installable via the Codex Plugins menu and adds to OpenAI's growing Codex user base of over 4 million weekly active users.
OpenAI added Codex Pets, an optional animated AI companion that floats over the Codex coding tool to surface real-time project status without leaving your editor. It ships with eight built-in pets and a custom creator to generate and share your own companions (including pop-culture figures like Clippy and even Sam Altman). Access is via Settings > Appearance or hotkeys such as /pet, Wake Pet, or Cmd/Ctrl-K.
OpenAI added optional AI-generated pets as live overlays in Codex, displaying Codex activity with a floating companion you can summon via /pet or hatch via /hatch. With eight built-in pets (and user-generated ones), these AI pets run on Windows and macOS, helping users see Codex status without switching apps. A limited promo also offers 30 days of ChatGPT Pro for 10 favorite companions.
Cursor rolled out Glass, a new orchestration layer to manage parallel AI coding agents; OpenAI released a codex-plugin-cc for Anthropic’s Claude Code, enabling Codex to run as a subagent inside Claude Code; and Codex can review Claude output via a cross-provider review gate. The three launches demonstrate a composable AI-coding stack—distinct layers for orchestration, execution, and review—rather than a single merged product. This pattern mirrors traditional dev-tool stacks and signals interoperability as a core trend for the AI-coding era, backed by Claude Code’s popularity and Codex’s large user base.
Google released a GitHub-hosted Google Workspace CLI that streamlines AI-agent integration with Gmail, Drive, and Docs, enabling tools like OpenClaw to connect to core Workspace data more easily. The tool, part of Google's developer-samples and not officially supported, also includes MCP (Model Context Protocol) integration options, signaling Google’s move to make Workspace more agent-ready for AI assistants.
Roku’s OS 15.1 update rolls out with a new HLS manifest-based seeking mode (EXT-X-START) for exact video starts, adds Perfetto tracing for app debugging via External Control Protocol and WebSocket, and deprecates roString.AppendString in favor of SetString, aiming to improve playback precision and developer workflow; initial rollout started after beta testing.
ZDNET reveals 11 hidden Fire TV remote button combos that unlock extra menus, reset options, accessibility tools, and quick tweaks—from cycling display resolutions and rebooting to entering developer tools or pairing a remote. Shortcuts include: adjust display resolution (Up + Rewind), restart (Select + Play/Pause), factory reset (Back + Right), reset remote (Left + Menu + Back), pair remote (Home), open Quick Settings (long-press Home), change Picture mode (Home → Picture), show Text Banners (Rewind + Fast-Forward), Screen Magnifier (Back + Fast-Forward), VoiceView (Back + Menu), and open Developer Tools (Select + Down, then Menu). Availability varies by model and firmware; ensure software is up to date. Factory resets erase data, so use cautiously.
Google has launched Gemini CLI Extensions, allowing third-party companies to integrate their tools into its command-line AI system, Gemini CLI, with initial extensions from Figma, Stripe, and Google’s own image generator, fostering an open ecosystem for developers.
OpenAI has launched AgentKit, a comprehensive toolkit designed to help developers easily build, deploy, and optimize AI agents, signaling a move to increase adoption and compete in the autonomous AI agent market. The toolkit includes visual design tools, chat interfaces, performance evaluation features, and secure integrations, demonstrated by a live build in under eight minutes, with several partners already scaling agents using it.
Claude Code has been upgraded with a native VS Code extension, enhanced terminal interface, and checkpointing for autonomous and complex development tasks, enabling more efficient and confident coding workflows with new features like subagents, hooks, and background tasks.
Google's senior director of product management, Ryan Salva, discusses how AI tools like Gemini CLI are transforming coding, emphasizing the shift towards agentic programming where developers focus more on high-level design and problem-solving, with AI handling much of the coding and troubleshooting. The adoption of AI coding tools is accelerating, and Salva envisions a future where developers act more as architects than traditional coders, with less time spent in IDEs and more on requirements and system design.
Microsoft is integrating OpenAI's GPT-5 into its products, including Microsoft 365 Copilot, Microsoft Copilot, GitHub Copilot, and Azure AI Foundry, enhancing reasoning, coding, and chat capabilities across consumer, developer, and enterprise platforms, with a focus on safety and efficiency.
The article discusses the slow response times of large language model (LLM) assisted workflows compared to traditional tools, highlighting experiences with AI agents in coding and automation, and emphasizing the importance of speed and interactivity in developer productivity. It also touches on UI design, web performance, and the value of speed in software development and user experience.