What a dormant agent costs
A million dormant agents written to disk and read back: 477 bytes of state each, 455 MB for the million, and a resume in 0.034 ms. Measured on a laptop, against a competitor figure that was modelled and never billed.
node fleet/fleet.mjs /tmp/fleet
prints the table on this page — transcribed from bench/README.md, the pass of 2026-09-07
- harness
- hanzoai/benchmarks · fleet
- our paper
- What a Dormant Agent Costs
Results
one million agents · an M-series laptop · the pass of 2026-09-07
Results
| measurement | Hanzo, measured | the published figure |
|---|---|---|
| state per dormant agent | 477 bytes | ~1 MB, a competitor’s own modelled assumption |
| one million dormant agents on disk | 455 MB | ~977 GB at that assumption |
| dormant agents written per second | 309,789 | — |
| resume one, in process | 0.034 ms | — |
The right-hand column is not a competitor’s measurement. It is the per-agent figure a competing platform assumes in its own published arithmetic, marked there as modelled and never billed. Ours is a directory you can list. The distance between the two is about 2,200× and most of it is the difference between an assumption and a file.
What this does not measure
A dormant agent is not a running one. This number is the floor, and the floor is the easy part. What a live agent costs is a different measurement with a different command — 601 bytes of heap and 125 ns to spawn.
What this does not measure
One machine, one day. This is a single pass on one laptop. It is reproducible by one command and it is not a fleet of machines under load, so read it as a floor that has been established rather than as a service level.
What is measured
A million agents are created, written to disk, and read back. What is counted is the state a dormant agent occupies — the row that has to exist for an agent to be resumable at all — the rate at which those rows can be written, and the time to bring one back. Nothing is running while the measurement is taken, which is the point: an agent platform’s floor is what it costs to keep an agent that is doing nothing.
node fleet/fleet.mjs /tmp/fleet
PreviousLoCoMo-Conv · All Benchmarks Board · NextLive agent footprint
Related in runtime
Live agent footprintSandbox cold start- Other benchmarks
LoCoMo · MemoryAgentBench · LongMemEval · CronQuestions · RepoBench-R · LoCoMo · subject scope · LoCoMo-Conv · Engine prefill on CUDA vs llama.cpp · GPQA-Diamond
harness and the committed table: hanzoai/benchmarks · fleet · the paper: What a Dormant Agent Costs
Build on Hanzo Cloud
Hanzo AI Cloud