Hacker News

Show HN: Scopo, Cmd+Tab scoped to the current macOS Space

Hacker News - Wed, 03/04/2026 - 4:46pm

I built Scopo after reading Theo's [https://x.com/theo] post about the "Agentic Code Problem". The reality that developers now work on 3-4 projects simultaneously and spend more time switching between windows than actually building.

The core idea: macOS Spaces are already project boundaries. Why doesn't Cmd+Tab respect them?

Scopo replaces the system Cmd+Tab with one scoped to your current Space. Each Space is a project context. You see 3-4 relevant windows instead of a bunch of unrelated windows and apps.

I built it for myself, used it for weeks on my work machine, and realized I couldn't work without it when I switched to a machine that didn't have it.

Some implementation details:

- CGEventTap to intercept Cmd+Tab before the Dock handles it - Moving windows between spaces on macOS 15 is hard — all SLS/CGS private APIs are broken without SIP disabled. Scopo simulates a Mission Control drag (same technique as Hammerspoon's Drag.spoon) - TF-IDF + cosine similarity for smart window-to-project matching

Built with Swift/AppKit

https://scopo.app

First time launching something, would genuinely appreciate any feedback on the product or the implementation.

Comments URL: https://news.ycombinator.com/item?id=47254374

Points: 2

# Comments: 0

Categories: Hacker News

Linux Signalfd Is Useless

Hacker News - Wed, 03/04/2026 - 4:42pm
Categories: Hacker News

Open Claw Agentic Monitoring

Hacker News - Wed, 03/04/2026 - 4:04pm

Comments URL: https://news.ycombinator.com/item?id=47253808

Points: 1

# Comments: 0

Categories: Hacker News

At Arms over Anthropic

Hacker News - Wed, 03/04/2026 - 3:58pm
Categories: Hacker News

Show HN: I built a tamper-evident evidence system for AI agents

Hacker News - Wed, 03/04/2026 - 3:56pm

The demo loads two runs directly in your browser — no signup, no uploads, no network calls after page load.

Frank: a conservative agent. Verification returns VALID. Phil: an aggressive agent with tampered evidence. Verification returns INVALID and points to the exact line where the chain breaks.

The problem I was solving: when an AI agent does something unexpected in production, the post-mortem usually comes down to "trust our logs." I wanted evidence that could cross trust boundaries — from engineering to security, compliance, or regulators — without asking anyone to trust a dashboard.

How it works:

- Every action, policy decision, and state transition is recorded into a hash-chained NDJSON event log - Logs are sealed into evidence packs (ZIP) with manifests and signatures - A verifier (also in the demo) validates integrity offline and returns VALID / INVALID / PARTIAL with machine-readable reason codes - The same inputs always produce the same artifacts — so diffs are meaningful and replay is deterministic

The verifier and the UI are deliberately separated. The UI can be wrong. The verifier will still accept or reject based on cryptographic proof.

Built this before the recent public incidents around autonomous agents made it topical. Happy to answer questions about the architecture, the proof boundary design, or the gaps I'm still working on.

Comments URL: https://news.ycombinator.com/item?id=47253678

Points: 2

# Comments: 0

Categories: Hacker News

Pages