# Dormant agent cost benchmark — Hanzo AI

> A million dormant agents written to disk and read back: 477 bytes of state each, 455 MB for the million, 309,789 written per second, and a resume in 0.034 ms. A file you can list, against a competitor figure that was modelled and never billed.

[Benchmarks](https://hanzo.ai/benchmarks) / Fleet residency

measured

# 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.

harness

[hanzoai/cloud · bench/fleet](https://github.com/hanzoai/cloud/tree/main/bench/fleet)

our paper

[What a Dormant Agent Costs](https://github.com/hanzoai/papers/tree/main/hanzo-dormant-agents)

`node fleet/fleet.mjs /tmp/fleet`prints the table on this page — transcribed from bench/README.md, the pass of 2026-09-07

## 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.

## Results

one million agents · M-series laptop · the pass of 2026-09-07

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 187 ns to spawn](https://hanzo.ai/benchmarks/goroutine) — and what it costs to give one a shell is a third one, at [150.8 ms for a cold container](https://hanzo.ai/benchmarks/sandbox).

The line that grows is not agents. A dormant agent stays 477 bytes; its transcript does not. At 2 KB retained per call, a billion calls a month is 22 TB after a year, and history eventually exceeds compute. Any cost claim built on the row size above is a claim about the wrong axis, and this page would rather say that than let the 477 be read as the whole bill.

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.

## The other benchmarks

[LoCoMo](https://hanzo.ai/benchmarks/locomo) · [MemoryAgentBench](https://hanzo.ai/benchmarks/memoryagentbench) · [LongMemEval](https://hanzo.ai/benchmarks/longmemeval) · [RepoBench-R](https://hanzo.ai/benchmarks/repobench-r) · [LoCoMo · subject scope](https://hanzo.ai/benchmarks/locomo-subject-scope) · [LoCoMo-Conv](https://hanzo.ai/benchmarks/locomo-conv) · [Live agent footprint](https://hanzo.ai/benchmarks/goroutine) · [Sandbox cold start](https://hanzo.ai/benchmarks/sandbox) · [Inference vs llama.cpp](https://hanzo.ai/benchmarks/inference) · [GPQA-Diamond](https://hanzo.ai/benchmarks/gpqa) · [all of them, and the head-to-head](https://hanzo.ai/benchmarks)

harness and the committed table: [hanzoai/cloud · bench/fleet](https://github.com/hanzoai/cloud/tree/main/bench/fleet) · the paper: [What a Dormant Agent Costs](https://github.com/hanzoai/papers/tree/main/hanzo-dormant-agents)