Automatic Fileless Malware Detection via eBPF Probes and LLMs
eBPF kernel hooks give LLMs direct system state access without command probing.
A zero-overhead CLI tool for capturing stdout/stderr output from a running process (and optionally its entire descendant tree) using eBPF tracepoints. Useful for attaching to processes that have already started, that redirect their output to `/dev/null`, that are buried inside a service manager, or that you simply don't want to restart.
eBPF-based live process I/O capture; clever kernel approach but narrow use case.
DevOps engineers, sysadmins, debugging systems without access to restart processes
strace · systemd journald · bpftrace
eBPF kernel hooks give LLMs direct system state access without command probing.
Steers AI toward naive solutions so candidate skill actually matters again.
Screen OCR search with redaction in a single Swift CLI—no dependencies beyond macOS.
Grades how candidates use AI, not just their output—finally addresses the AI-cheating problem.
The core idea — one-tap, one-field capture and deferred processing — is simple and genuinely helpful for attention-challenged workflows; the app pairs that flow with Workspace and Timeline views so you can act from already-sorted items. It’s not reinventing GTD, but the mobile-first PWA, offline/local storage hints, and a focused UI show someone trimmed features ruthlessly for speed; the obvious tradeoffs are sync behind a paywall and the limitations of PWA distribution versus native apps.
Direct eBPF kernel tracing beats slow CLI probing for AI sysadmin tasks.