面向使用 Claude Code、Xcode 等 AI 编程代理的开发者，实时展示每个代理的会话、构建、测试与截图，本地读取磁盘数据，帮助掌握代理后台行为。
热门评论
PH 用户
Hi Product Hunt 👋
I run Claude Code against my Xcode projects all day — from the terminal and, since Xcode 27, as agents Xcode launches itself. Xcode's view of what they do is one word: "Idle". The builds, the failing tests, the screenshots they take on the simulator — all of it lands on disk and nothing shows it. Agent test results in particular don't even get a result bundle; they exist only as a summary file in a temp folder.
Agent Activity reads those files and shows them as a live timeline per session: builds with errors parsed to file and line, test runs by target, previews and screenshots with the UI tree beside them, and which agents Xcode trusts to touch which folders.
No account, no server of ours. No transcript, message or build-log content, project name or project path leaves the Mac. It asks once, before sending anything; after that, two switches send usage and crash data, keyed to this install, independently in Settings. They can carry an unrecognised record type's name (its first 60 characters), and a crash report the app's own install path, which names your macOS account if it's under your home folder, and the crash's error message, whose text the app can't control when macOS raised it. Sandboxed, asks for exactly the folder access it needs and explains each grant.
It's for people running coding agents in Xcode — a small crowd today, growing with every Xcode release. It doesn't launch or control agents; it shows what they did. Claude Code in v1, more agents by adapter.
Mac App Store: https://apps.apple.com/us/app/ag... · https://le-max-app.com/apps/agen... · a direct build with a trial follows later
I'll be here all day — ask me anything about the formats, the sandbox, or why the test results were the last straw.
PH 用户
saw a forum post this morning making the case that this whole category - Cubicle, Singularity, bmux, this one - is a symptom, not a product, because agents fail quietly and a live view only catches it if someone's actually watching. your build/test/screenshot timeline is honest about that since it's just surfacing what's on disk, not claiming confidence or correctness. but that's also my question: when a test run shows green and a screenshot looks fine, does Agent Activity ever flag the result as suspicious on its own, or is the value entirely "the data exists now, go look at it yourself"? genuinely not sure which answer I'd prefer.
I run Claude Code against my Xcode projects all day — from the terminal and, since Xcode 27, as agents Xcode launches itself. Xcode's view of what they do is one word: "Idle". The builds, the failing tests, the screenshots they take on the simulator — all of it lands on disk and nothing shows it. Agent test results in particular don't even get a result bundle; they exist only as a summary file in a temp folder.
Agent Activity reads those files and shows them as a live timeline per session: builds with errors parsed to file and line, test runs by target, previews and screenshots with the UI tree beside them, and which agents Xcode trusts to touch which folders.
No account, no server of ours. No transcript, message or build-log content, project name or project path leaves the Mac. It asks once, before sending anything; after that, two switches send usage and crash data, keyed to this install, independently in Settings. They can carry an unrecognised record type's name (its first 60 characters), and a crash report the app's own install path, which names your macOS account if it's under your home folder, and the crash's error message, whose text the app can't control when macOS raised it. Sandboxed, asks for exactly the folder access it needs and explains each grant.
It's for people running coding agents in Xcode — a small crowd today, growing with every Xcode release. It doesn't launch or control agents; it shows what they did. Claude Code in v1, more agents by adapter.
Mac App Store: https://apps.apple.com/us/app/ag... · https://le-max-app.com/apps/agen... · a direct build with a trial follows later
I'll be here all day — ask me anything about the formats, the sandbox, or why the test results were the last straw.