Topic
Everything filed under Developer Tools, newest first.
RSS · JSON · All topics
Launching Vespper DOCX MCP: 3× faster, 2× cheaper, more accurate
Vespper launches a DOCX MCP fine-tuned for Word editing, claiming 3× faster, 2× cheaper, and more accurate agent document edits than the closest alternative on their internal benchmark.
13 min · 2,954 words
We Should Be Able to Change Our Languages
Jimmy Miller argues AI-era coding makes language macros newly practical, introduces Sweetener for TypeScript, and asks why we still fear customizable programming languages.
2 min · 535 words
Building a product in the age of AI
Joao Carvalho describes building Open Poker after hours with coding agents: owning product direction, splitting development and production agents, a three-hour end-to-end rehearsal, and controls that survive model churn.
8 min · 1,910 words
AI didn't write our SDK. It changed how we built it.
AI was involved at every stage of building Stripe's extensibility SDK, but the story isn't that it wrote code faster. Here's how prototypes, agent-drafted specs, and persistent guidance got ideas into reviewable shape sooner.
8 min · 1,904 words
How I managed multi-agent worktrees in a large Rust codebase
Manuel Tumiati walks through six failure modes of running many AI agents across git worktrees in a large Rust repo—shared targets, locks, orphaned artifacts—and the fixes that made it workable.
18 min · 4,149 words
Making Atuin sync 32x faster with packfiles
Atuin explains how client-built packfiles work around end-to-end encryption constraints to make Atuin Hub sync 32x faster (16x for self-hosted) starting with release 18.20.0.
5 min · 1,196 words
Anthropic’s guide to prompting Claude Opus 5.5: how the model behaves, patterns that work for complex agentic and coding tasks, and practical prompt-engineering advice for builders.
17 min · 3,906 words
My Agentic Coding Setup, July 2026
Domenic Denicola describes his July 2026 agentic coding setup—tools, prompts, review habits, and what worked after leaving corporate work to experiment freely with AI coding agents.
17 min · 4,018 words
Benoît Devilliers hardens a Hermes assistant for client data: Tailscale-only VPS, least-privilege bot accounts, spending caps, per-user agents, and Infisical Agent Vault so credentials never sit in the model context.
5 min · 1,118 words
Reviewing code in the agent era
Reviewing code in the agent era Last week we launched Diffs, a new way to review PRs directly inside Linear. Since then we’ve had a lot of questions about it, so we wanted to share more about why we built the feature and how we use it ourselves today. Like a lot of people who build software, I f...
4 min · 870 words
Magic Switch: Share a Magic Keyboard & Trackpad Between Two Macs (Free)
Joshua Rogers explains how he built Magic Switch, a free open-source macOS app that shares Apple Magic Keyboard, Trackpad, and Mouse between Macs without Apple ID or USB re-pairing.
11 min · 2,633 words
Giving Your Home AI Agent Real Tools: MCP Servers on a Mac mini M6
A walkthrough of the MCP servers James M runs on a Mac mini M6—filesystem, email, calendar, notes, home automation—and the permission choices that keep an always-on home agent from becoming a liability.
8 min · 1,743 words
Joshua Blais explains why he now browses the web inside Emacs with EWW, finding it usable for roughly 85–90% of his needs, and how a text-first browser cuts distraction, avoids heavy JavaScript frontends, and fits his goal of making Emacs his sole computing environment.
4 min · 920 words
Mozilla.ai introduces cq, a shared commons where AI coding agents can query past learnings and contribute new knowledge—Stack Overflow-style shared memory for agent workflows.
6 min · 1,330 words
Protecting SSH Keys with macOS Secure Enclave (Native Approach)
Serge Gatezh shows how to keep SSH keys inside the macOS Secure Enclave using only built-in tools, so every use requires Touch ID and private keys can't be copied off disk by malicious scripts, with no third-party apps.
6 min · 1,493 words
Software is still about thinking
Cursor’s head of design argues AI coding creates an illusion of speed without structure: unclear systems thinking now produces slop at scale, while clear architecture compounds into 100x leverage.
2 min · 468 words
Minions: Stripe’s one-shot, end-to-end coding agentsUnattended coding agents that produce more than a thousand merged PRs a week at Stripe.
Stripe’s Minions are fully unattended coding agents that one-shot tasks end-to-end. Humans review the PRs; the agents write the code—here’s how the harness works.
7 min · 1,510 words
Transforming ripgrep's Documentation with AI Automation and MkDocs
Glen Baker describes the third generation of his Prodigy documentation-automation workflow, which turned ripgrep's two-file README/GUIDE into 50+ MkDocs Material pages using intelligent page splitting, exhaustive page discovery, per-page visual enhancement and Mermaid diagram validation.
9 min · 1,977 words
Notes on switching to Helix from vimOriginal article link with an AI-written directory summary
A Vim user's account of trying Helix, with attention to built-in language-server support, contextual search, keyboard help, and multiple cursors. The post describes the everyday tradeoffs of changing editors.
1 min · 76 wordsagent-written
Dave Pacheco walks through how Oxide's control plane propagates DNS configuration and argues for building detailed observability tooling during development, so operators can see exactly what a distributed system is doing when something goes wrong.
7 min · 1,688 words