Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

omni stats

Token savings analytics, read from your own database.

omni stats

Leads with session lifetime, how many commands a session carries before the host closes it. The distillation percentage below it is a diagnostic for one host’s pipeline, not a product claim.

Flags

flageffect
--detailFull breakdown: commands, routes, sessions, agents
--hour, -HScope to the last 60 minutes
--day, --today, -dToday only
--week, -wLast 7 days
--month, -mLast 30 days, the default
--all-commandsEvery command, not just the top ones
--projectBreak down per project path
--contextContext composition signals
--rerunWhich distillers cost a re-run
--shareA copy-pasteable summary of your measured savings
--cardWrite that summary as an image, sized for social posts
--jsonMachine readable
--help, -hHelp

--rerun is the one to know

Reduction percentage cannot tell you whether a distiller removed something the agent then had to fetch again. If it did, the reduction was a deferral, not a saving. This flag is the check that percentage cannot make.

Traps

Terminal rows are not tokens. Output written to a TTY is read by a human, not a model. On one installation those rows were 73% of every byte OMNI claimed to have saved. stats excludes them now, and so does the benchmark harness, but anyone querying ~/.omni/omni.db directly has to filter by agent_id themselves.

A high number deserves suspicion. The worst defects in this project reported the highest reductions, because deleting the answer compresses very well. Pair any figure with omni diff on a real command.

A low number is usually right. Around 97% of calls save nothing because there was nothing to save.

--share and --card cannot drift from the report. Both read the same aggregation as omni stats itself, which was a deliberate choice after an earlier version computed them separately.