SmitheryListed

What's Running

Ground truth for agent fleets. Tells your agent what is actually running on the machine — live agent sessions, listening TCP ports, loaded daemons, and system load — read straight from the OS (ps / lsof / launchctl / systemctl / df), never from docs, transcripts, or memory files. If you run more than one coding-agent session, you have seen the failure mode: an agent "health-checks" a service that died weeks ago, or reports a daemon as live because an old transcript said so. Model memory is a cache with no invalidation; the OS is the source of truth. Five read-only tools: whats_running (full snapshot), agent_sessions, listening_ports, daemons, system_stats. Read-only by construction — every command is a fixed binary with fixed flags via execFile, no shell, and nothing derived from model input is ever executed. macOS and Linux. MIT licensed. Free and MIT, with no telemetry and nothing held back. Built by Shift The Culture, who also publish two paid kits for the failure modes this server surfaces: https://shifttheculture.media/agent-tools

First seen 2 Oct 2026. Evidence as of 5 Oct 2026.