https://xeve.io/blog How Xeve's apps work, how we built them, and what we learn shipping them. https://xeve.io/blog/drivestream-road-trip-drive-recording-replay https://xeve.io/blog/drivestream-road-trip-drive-recording-replay Fri, 25 Sep 2026 00:00:00 GMT DriveStream DriveStream automatically logs every road trip — route, distance, moving time and top speed — with animated replay on the phone and a web companion. https://xeve.io/blog/rogr-find-crew-no-signal-uwb-gps https://xeve.io/blog/rogr-find-crew-no-signal-uwb-gps Thu, 24 Sep 2026 00:00:00 GMT Rogr When there's no signal, Rogr's Find uses Ultra Wideband at close range and GPS further out, all peer-to-peer with no internet. https://xeve.io/blog/how-drivestream-fuel-tracker-got-built https://xeve.io/blog/how-drivestream-fuel-tracker-got-built Wed, 23 Sep 2026 00:00:00 GMT DriveStream Fuel tracking was item three in DriveStream's first prompt. Here's how it went from a list item to a feature visible across the whole convoy. https://xeve.io/blog/cribbit-background-listening-pip-talkback https://xeve.io/blog/cribbit-background-listening-pip-talkback Tue, 22 Sep 2026 00:00:00 GMT Cribbit Cribbit's core monitoring is free. The one-time unlock adds background audio with the screen off, Picture in Picture, talk-back and lullabies. https://xeve.io/blog/how-we-built-drivestream https://xeve.io/blog/how-we-built-drivestream Sun, 20 Sep 2026 00:00:00 GMT DriveStream From a group-chat problem to a low-poly convoy map: the prompts and decisions behind the DriveStream iOS app. https://xeve.io/blog/rogr-offline-walkie-talkie-iphone https://xeve.io/blog/rogr-offline-walkie-talkie-iphone Thu, 17 Sep 2026 00:00:00 GMT Rogr Rogr turns two iPhones into a walkie-talkie using peer-to-peer Wi-Fi and Bluetooth. No internet, no network, no account required. https://xeve.io/blog/how-we-built-rogr https://xeve.io/blog/how-we-built-rogr Wed, 16 Sep 2026 00:00:00 GMT Rogr We built Rogr in two days using Claude Code, starting from Cribbit's transport layer. Here's how one prompt turned a plain communicator into a field radio. https://xeve.io/blog/how-we-animated-gobbl-pet-in-swiftui https://xeve.io/blog/how-we-animated-gobbl-pet-in-swiftui Tue, 15 Sep 2026 00:00:00 GMT Gobbl Gob, the pet in Gobbl's notch, is drawn in code with SwiftUI's Canvas. How its 17 moods work, who picks them, and how it stays cheap to run. https://xeve.io/blog/how-we-built-gobbl https://xeve.io/blog/how-we-built-gobbl Tue, 15 Sep 2026 00:00:00 GMT Gobbl Gobbl went from first commit to a notarized release in a day. Why the pet is a computer, how it types along with you, and the dictation that was too slow. https://xeve.io/blog/automated-time-tracker-for-developers https://xeve.io/blog/automated-time-tracker-for-developers Mon, 14 Sep 2026 00:00:00 GMT Orma Manual time tracking fails because it demands effort. Here is what automated time tracking captures and how it fits a developer's actual workflow. https://xeve.io/blog/cribbit-no-cloud-baby-monitor-iphone https://xeve.io/blog/cribbit-no-cloud-baby-monitor-iphone Mon, 14 Sep 2026 00:00:00 GMT Cribbit Cribbit turns two iPhones into an offline baby monitor. Here's how direct device-to-device video works, and what no cloud actually means. https://xeve.io/blog/how-we-built-cribbit https://xeve.io/blog/how-we-built-cribbit Mon, 14 Sep 2026 00:00:00 GMT Cribbit From the first prompt to TestFlight in two days — the mascot decisions, the missing encryption, and what shipping an offline app actually costs. https://xeve.io/blog/introducing-the-xeve-blog https://xeve.io/blog/introducing-the-xeve-blog Mon, 14 Sep 2026 00:00:00 GMT Xeve xeve.io is now the home of Xeve, the studio behind Orma, Cribbit, Rogr, DriveStream and TidyBug. This blog covers all five, and how we build them. https://xeve.io/blog/iphone-walkie-talkie-offline-no-cell-service https://xeve.io/blog/iphone-walkie-talkie-offline-no-cell-service Mon, 14 Sep 2026 00:00:00 GMT Rogr Rogr turns iPhones into walkie-talkies using peer-to-peer Wi-Fi and Bluetooth — the same radios as AirDrop. No internet, no account, no server. https://xeve.io/blog/keep-road-trip-convoy-together-drivestream https://xeve.io/blog/keep-road-trip-convoy-together-drivestream Mon, 14 Sep 2026 00:00:00 GMT DriveStream DriveStream puts every car on one live map with speed, fuel and shared ETAs. Here's what the iOS 26 convoy app actually does. https://xeve.io/blog/wakatime-alternative https://xeve.io/blog/wakatime-alternative Mon, 14 Sep 2026 00:00:00 GMT Orma WakaTime tracks editor keystrokes. If you want full app usage, health correlations, and GitHub activity alongside coding hours, here is what to look at instead. https://xeve.io/blog/xcode-deriveddata-cleanup-macos-developer https://xeve.io/blog/xcode-deriveddata-cleanup-macos-developer Mon, 14 Sep 2026 00:00:00 GMT TidyBug Xcode DerivedData, iOS device support, npm caches and Docker VMs quietly fill your Mac's disk. Here's where each one hides and how to remove it safely. https://xeve.io/blog/how-to-track-coding-time-2026 https://xeve.io/blog/how-to-track-coding-time-2026 Sun, 13 Sep 2026 00:00:00 GMT Orma WakaTime now tracks Claude Code sessions. Here's why that's a start, and what system-level tracking adds that heartbeat plugins alone can't give you. https://xeve.io/blog/set-up-automatic-time-tracking-mac https://xeve.io/blog/set-up-automatic-time-tracking-mac Sun, 13 Sep 2026 00:00:00 GMT Orma Automatic time tracking on Mac takes under five minutes to set up. Here is exactly what to install, what permissions to grant, and what you will see in the first week. https://xeve.io/blog/automatic-time-tracking https://xeve.io/blog/automatic-time-tracking Sun, 06 Sep 2026 00:00:00 GMT Orma WakaTime's data shows the average developer codes 51 minutes a day. If you rely on manual timers, you don't know your actual number — automatic tracking does. https://xeve.io/blog/vs-code-time-tracking https://xeve.io/blog/vs-code-time-tracking Mon, 31 Aug 2026 00:00:00 GMT Orma How to track your actual coding time in VS Code automatically. Heartbeat-based tracking by project, language, and file — and why editor-only data tells half the story. https://xeve.io/blog/automated-time-tracker https://xeve.io/blog/automated-time-tracker Mon, 24 Aug 2026 00:00:00 GMT Orma xeve tracks every app switch, coding session, and focus block on macOS and Windows automatically — no timers, no manual input, just real data about your day. https://xeve.io/blog/ai-pr-review-focus-time-collapse https://xeve.io/blog/ai-pr-review-focus-time-collapse Sun, 23 Aug 2026 00:00:00 GMT Orma LinearB's 8.1M PR dataset shows AI-generated pull requests wait 4.6x longer for reviewer pickup. The bottleneck isn't the code quality. It's that reviewers have 4.2 hours of focus and it was already spoken for. https://xeve.io/blog/agent-failure-unrecoverable-early-trajectory https://xeve.io/blog/agent-failure-unrecoverable-early-trajectory Sat, 22 Aug 2026 00:00:00 GMT Orma A July 2026 study on 3,843 CLI trajectories shows failure becomes unrecoverable early — well before most developers think to intervene. https://xeve.io/blog/jetbrains-agent-adoption-workflow-blind-spot https://xeve.io/blog/jetbrains-agent-adoption-workflow-blind-spot Fri, 21 Aug 2026 00:00:00 GMT Orma JetBrains' August 2026 survey found Claude Code overtook Copilot as the most-used AI tool at work — and that AI reshapes workflows in ways developers can't perceive. https://xeve.io/blog/kimi-k3-zero-cost-ai-baseline-collapse https://xeve.io/blog/kimi-k3-zero-cost-ai-baseline-collapse Thu, 20 Aug 2026 00:00:00 GMT Orma Kimi K3 hit GitHub Copilot on August 6 at $3/1M tokens with a FrontierSWE score of 81.2. When frontier coding AI costs this little, selective deployment ends — and so does your ability to measure what it does. https://xeve.io/blog/maintainer-disengagement-beats-burnout-data https://xeve.io/blog/maintainer-disengagement-beats-burnout-data Wed, 19 Aug 2026 00:00:00 GMT Orma Tidelift data shows 'loss of interest' (51%) ranks higher than 'burnout' (44%) in why open source maintainers quit. They're different conditions with different fixes. https://xeve.io/blog/github-agent-apps-lookup-mode-shift https://xeve.io/blog/github-agent-apps-lookup-mode-shift Tue, 18 Aug 2026 00:00:00 GMT Orma GitHub's Agent Apps embed Amplitude, LaunchDarkly, and PagerDuty in your PR. That solves the lookup problem. Mode shifts are something different. https://xeve.io/blog/cacm-neural-coding-end-of-software-engineering https://xeve.io/blog/cacm-neural-coding-end-of-software-engineering Mon, 17 Aug 2026 00:00:00 GMT Orma CACM's August 2026 issue argues neural coding may be the endpoint for software engineering as a rigorous discipline. The discipline isn't ending — but where it lives has moved. https://xeve.io/blog/meetings-doubled-peak-hours-developer-focus-2026 https://xeve.io/blog/meetings-doubled-peak-hours-developer-focus-2026 Sun, 16 Aug 2026 00:00:00 GMT Orma Hubstaff's 2026 study of 140,000 workers found meeting volume doubled and 26% of meeting time lands in the 9-11 AM window. The count isn't the problem — the timing is. https://xeve.io/blog/ai-agents-language-frontier-activation-band https://xeve.io/blog/ai-agents-language-frontier-activation-band Sat, 15 Aug 2026 00:00:00 GMT Orma A July 2026 panel study of 5,346 developers found active languages rose 2.5x at Claude Code adoption. The mechanism — an activation band of previously-too-hard technologies — reframes what AI productivity means. https://xeve.io/blog/nber-ai-coding-commits-vs-releases https://xeve.io/blog/nber-ai-coding-commits-vs-releases Fri, 14 Aug 2026 00:00:00 GMT Orma NBER tracked 100,000+ GitHub developers across three AI tool generations. Autonomous agents add 180% more commits. Actual releases are up 30%. Here's the gap. https://xeve.io/blog/ai-governance-gap-individual-developer https://xeve.io/blog/ai-governance-gap-individual-developer Thu, 13 Aug 2026 00:00:00 GMT Orma 94% of developers use AI in the build phase. 76% of organizations have no governance process for what it ships. The gap between those two numbers is absorbed by individual developers as invisible work. https://xeve.io/blog/ai-intent-debt-rationale-disappears https://xeve.io/blog/ai-intent-debt-rationale-disappears Wed, 12 Aug 2026 00:00:00 GMT Orma ACM Queue's August issue names a new type of debt: intent debt. AI produces technically correct code while erasing the reasoning behind every implementation decision. https://xeve.io/blog/ai-coding-trust-adoption-gap-productivity https://xeve.io/blog/ai-coding-trust-adoption-gap-productivity Tue, 11 Aug 2026 00:00:00 GMT Orma ACM's August myths paper buried the most important number: a 51-point gap between AI coding adoption and trust. That gap is where your productivity went. https://xeve.io/blog/coding-agents-clarification-gap-swe-chat https://xeve.io/blog/coding-agents-clarification-gap-swe-chat Mon, 10 Aug 2026 00:00:00 GMT Orma SWE-chat analyzed 6,000 real agent sessions: agents ask for clarification in 1.4% of turns. Users push back in 44%. The mismatch is structural, not incidental. https://xeve.io/blog/mid-level-engineers-ai-productivity-tax https://xeve.io/blog/mid-level-engineers-ai-productivity-tax Sun, 09 Aug 2026 00:00:00 GMT Orma LeadDev's July 2026 data names mid-level engineers as the hidden absorbers of AI productivity — doing institutional judgment work that no metric counts and no model can learn. https://xeve.io/blog/ai-approval-codebase-knowledge-erosion https://xeve.io/blog/ai-approval-codebase-knowledge-erosion Fri, 07 Aug 2026 00:00:00 GMT Orma Info-Tech's July 2026 study found AI code requires MORE testing despite productivity gains. The reason: approving code isn't the same as understanding it. https://xeve.io/blog/cursor-router-model-opacity-workflow-signal https://xeve.io/blog/cursor-router-model-opacity-workflow-signal Thu, 06 Aug 2026 00:00:00 GMT Orma Cursor Router cuts AI coding costs 60% by routing automatically. The opacity means you can no longer isolate model behavior from your own performance variance. https://xeve.io/blog/shadow-ai-codebase-provenance-gap https://xeve.io/blog/shadow-ai-codebase-provenance-gap Wed, 05 Aug 2026 00:00:00 GMT Orma Sonar's 2026 State of Code found 35% of developers use AI via personal accounts. That 42% of committed code being AI-generated? You can trace maybe two-thirds of it.