Share by installs
Share by installs
No public aggregate yet. This appears when the reporting conditions are met.
Cumulative · Share of installation counts across listed agents. Installations using multiple agents are counted more than once.
AGENTCAT / TRENDS
A working day.
With a few more cats.
Which agents do we work with? Which cats keep us company? Explore the patterns in AgentCat’s anonymous aggregates.
AGENTCAT / DATA
Loading public aggregates.
01 / Agents
The agents we work with
Compare the share of installations with the share of tokens processed.
Estimated token share
Estimated token share
No public aggregate yet. This appears when the reporting conditions are met.
Cumulative · Share of estimated tokens across listed agents. This is not a billing or cost comparison.
02 / Models
The models in use
A model’s rank changes when you count installations or tokens.
Top 5 by installs
Top 5 by installs
No public aggregate yet. This appears when the reporting conditions are met.
Cumulative · Share of installation counts within these five models. Multi-model installations can appear more than once.
Top 5 by estimated tokens
Top 5 by estimated tokens
No public aggregate yet. This appears when the reporting conditions are met.
Cumulative · Share of estimated tokens within these five models.
03 / Mascots
The company we keep
Who spends the most time alongside us? A look at activity recorded with each mascot.
The company we keep
The company we keep
No public aggregate yet. This appears when the reporting conditions are met.
Cumulative · Share of activity events within these five mascots, rather than a ranking by users.
04 / Activity
The rhythm of work
Busy days, working hours, and where usage is concentrated.
Activity by weekday
Activity by weekday
No public aggregate yet. This appears when the reporting conditions are met.
Last 30 days · KST · Each day’s share of all activity events.
Activity by hour
Activity by hour
No public aggregate yet. This appears when the reporting conditions are met.
Share of published hourly activity. All bars use the same percentage scale.
Highest daily usage
Highest daily usage
No public aggregate yet. This appears when the reporting conditions are met.
Published daily aggregate · No user identity is shown.
How usage is distributed
How usage is distributed
No public aggregate yet. This appears when the reporting conditions are met.
Last 30 days · Share of estimated tokens from the top 10% of installations.
05 / Quota weather
Unofficial quota weather
Aggregate quota signals and external reset forecasts, with their sources.
CODEX / COMMUNITY SIGNAL
Unofficial quota weather
Waiting for recent anonymous quota pulses.
How to read these numbers
These are AgentCat’s public anonymous aggregates. Installation counts use anonymous installation IDs. Small samples are withheld, and missing data is never shown as zero. Users of multiple agents or models can be counted in more than one category.
Token figures are estimates adjusted by the server for provider differences. Some records without output tokens use total tokens divided by 50. Where provider samples are large enough, the highest and lowest 5% of per-user totals are excluded. These figures cannot establish exact billing or costs.
Agents, models, and mascots are cumulative; weekdays and usage distribution cover 30 days. Rounding can keep percentages from adding to 100%. The update above is the newest timestamp in the response, including external forecasts; individual metrics need not share that timestamp.
View public data ↗ Data policy ↗