AI agents now write code, fix bugs, and ship to production. But in order to do useful work, agents require credentials. At 1Password, one of our core AI security principles is that raw credentials should never be directly exposed to LLMs, but all too often, that’s exactly what happens: most teams sacrifice security for speed and hand agents secrets in plaintext.
The shortcuts behind that…
A small fun fact for iOS and MacOS automations
Virgin Atlantic says OpenAI Codex helped developers shrink legacy codebases, improve testing coverage, and dramatically speed up software development during high-pressure airline deployments.
1Password and OpenAI are teaming up to make AI coding workflows safer by keeping credentials out of prompts, repositories, and model context entirely.
GitHub has launched a standalone Copilot desktop app in technical preview, moving beyond the IDE to introduce a dedicated cockpit for agentic development. The app enables developers to manage parallel, isolated agent sessions directly from GitHub issues, while introducing "Agent Merge"—a feature that autonomously fixes CI failures and handles code reviews to streamline the entire PR lifecycle.
Rocket.net is letting AI assistants like ChatGPT take control of WordPress management using MCP, and since NERDS.xyz runs on it, I’m about to find out if this is actually useful or just more AI hype.
AI coding agents are becoming more capable, but evaluating them is harder than it looks. Most benchmarks focus on a single dimension of agent capabilities; for instance, the popular SWE-Bench benchmark only focuses on fixing issues on open source Python repositories. Real-world software engineering involves fixing bugs of course, but it is a lot more […]
Notepad++ for Mac is finally here as a real native macOS app, bringing the familiar Windows editor experience without relying on compatibility layers.
Another month, another record number of pull requests merged! August flew by, and with it came 447 pull requests from Servo contributors. It was also the final month of our Outreachy cohort; you can read Jerens’ and Uthman’s blogs to learn about how it went!
Our big new feature this month is rendering inline SVG elements (@mukilan, @Loirooriol, #38188, #38603). This…
GitHub Copilot CLI’s "Rubber Duck" experimental feature uses cross-family model collaboration (Claude + GPT-5.4) to catch architectural flaws and reduce logic errors.
A newly released open source framework called SentiAvatar aims to make AI avatars behave more like real people during conversation. The project includes a motion dataset with 21,000 clips, a foundation model trained on hundreds of hours of motion data, and a system that synchronizes speech, facial expressions, and body gestures in real time. If the technology works as advertised, it could help…
Building apps with AI is easy now. Running them is not. Hosting.com thinks it has a solution, but does it really fix the problem?
GitLab is pushing agentic AI deeper into development workflows with version 18.10, but developers may question whether they actually need it.
OpenAI wants Astral’s tools to turn Codex into something bigger than a code generator, and that could reshape how Python developers work.
OpenAI introduces GPT-5.4 mini and nano, two smaller AI models built for speed, efficiency, and scalable coding workflows.
GitHub Copilot, the coding agent, now integrates with Jira. Assign issues to Copilot and get draft PRs — no context switching between planning and code.
ExpressVPN has launched the beta of what it calls the industry’s first VPN MCP server, letting AI tools read and configure VPN settings directly from developer workflows.
The Eclipse Foundation launches a new framework for the Open VSX Registry, enhancing security features and transitioning to a hybrid architecture. With support from AI tool provider Cursor, this initiative aims to promote safer software supply chains.
Discover how Postman’s new feature allows software engineering teams to manage API specifications, collections, and environments directly from Git repositories, simplifying workflows for AI agents in the development process.
Thomas Dohmke's new company, Entire, aims to redefine the software development lifecycle for AI-driven coding by focusing on post-code generation processes. With a $60 million seed round, Entire's first product, Checkpoints, enhances visibility into AI-generated code, addressing the challenges of governance and review for DevOps teams.
Discover why learning jq isn't just about boosting your productivity, it's about becoming a more curious developer
A journey through text editors and how I landed on Zed after years of Neovim
A deeper look at why a integrated terminal workflow is more than just using vim
Some tips on how to eaily move to VSCode as a Neovim user (sorry Primeagen)