# Live agent footprint benchmark — Hanzo AI > A running agent as a goroutine: 601 bytes of heap each, 187 ns to spawn, 114 ms to wake a million — against a V8 isolate measured here at 1.00 MiB and 0.59 ms. Plus the three language runtimes that fit inside one. [Benchmarks](https://hanzo.ai/benchmarks) / Live agent footprint measured # An agent as a goroutine A dormant agent is a row; a running one still has to hold its place. 601 bytes of heap per live agent, 187 ns to spawn one, 114 ms to wake a million — and the three language runtimes that can sit inside one. harness [hanzoai/cloud · bench/goroutine](https://github.com/hanzoai/cloud/tree/main/bench/goroutine) our paper [What a Dormant Agent Costs](https://github.com/hanzoai/papers/tree/main/hanzo-dormant-agents) `cd goroutine && go build -o /tmp/g . && /tmp/g`prints the table on this page — transcribed from bench/README.md, the pass of 2026-09-07 ## What is measured A dormant agent is a row on disk. An agent that is running still has to hold its place, and the question is what that place costs. Here it is a goroutine: the heap it occupies, the time to start one, and the time to wake a million of them at once. The comparison column is what a platform built on V8 isolates publishes for the same two quantities. ## Results M-series laptop · the pass of 2026-09-07 · memory was identical on all five runs; timings are medians measurement Hanzo, measured the published figure heap per live agent 601 bytes 1.2 MB per isolate, isolated-vm one million live agents 573.0 MB — spawn one 187 ns 2.79 ms, isolated-vm wake one million 114 ms — 114 ns each — 601 bytes against a 128 MB container floor is about 223,000×, and against a V8 isolate about 1,700× — and that second one is a goroutine against a JavaScript VM, so read it as what each primitive costs rather than as one beating the other. The isolate column is measured here rather than cited: a fresh isolated-vm isolate is 1.00 MiB and 0.59 ms on this laptop, close to the 1.2 MB attributed to it, because a megabyte is what any isolate costs including one of ours. The number that matters more for an interactive system is the 187 ns: an agent that costs nothing to start does not need to be kept warm, and a pool is a thing you maintain because starting was expensive. ### What can run inside one the same pass · instantiate is per context; call is a warm invocation runtime language instantiate call wazero WASM — any language that targets it 8.9 µs 23 ns goja JavaScript 2.7 µs per VM 818 ns warm eval gpython Python 29.9 µs per context — WASM is not one language: CPython, QuickJS for TypeScript, Rust and Go all target it. A V8 isolate is JavaScript, and only JavaScript. ## How to get this wrong Benchmark a built binary. Under `go run` the compile is counted and spawn reads 253 ns instead of 187 ns — a 35% error from the command you used to start the measurement. The reproduce line on this page builds first for exactly that reason. A goroutine is not a sandbox. These agents share an address space. Nothing here is a security boundary, and an agent that must run untrusted code needs one — which costs [150.8 ms for a cold container](https://hanzo.ai/benchmarks/sandbox), four orders of magnitude more than the spawn above. The two numbers answer different questions and a platform needs both. One machine, one day. A single pass on one laptop, reproducible by one command. It establishes a floor; it is not a service level under load. ## 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) · [Fleet residency](https://hanzo.ai/benchmarks/fleet) · [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/goroutine](https://github.com/hanzoai/cloud/tree/main/bench/goroutine) · the paper: [What a Dormant Agent Costs](https://github.com/hanzoai/papers/tree/main/hanzo-dormant-agents)