mirror of
https://github.com/hanzoai/site.git
synced 2026-11-21 01:07:08 +00:00
platform.hanzo.ai is the platform console (with cloud.hanzo.ai redirecting to it at the edge). Point the remaining cloud.hanzo.ai links on /benchmarks and /philosophy directly at https://platform.hanzo.ai. Claude-Session: https://claude.ai/code/session_015XYKLix9PSyn6Jw2HWKprk
1 line
3.2 KiB
JSON
1 line
3.2 KiB
JSON
{"text":["Fleet residency","Benchmarks","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/benchmarks · fleet","our paper","What a Dormant Agent Costs","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","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.","dormant","Results","one million agents · an 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","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 —","A dormant agent is not a running one.","601 bytes of heap and 125 ns to spawn","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.","One machine, one day.","Hanzo AI Cloud","Build on Hanzo Cloud","Start on Hanzo Cloud","View Models & Pricing","Previous","LoCoMo-Conv","All Benchmarks Board","Next","Live agent footprint","Related in runtime","Sandbox cold start","Other benchmarks","LoCoMo","MemoryAgentBench","LongMemEval","CronQuestions","RepoBench-R","LoCoMo · subject scope","Engine prefill on CUDA vs llama.cpp","GPQA-Diamond","harness and the committed table:","· the paper:"],"links":["/benchmarks","https://github.com/hanzoai/benchmarks/tree/main/fleet","https://github.com/hanzoai/papers/blob/main/site/public/pdfs/hanzo-dormant-agents.pdf","/benchmarks/goroutine","https://platform.hanzo.ai","/pricing","https://hanzo.ai/benchmarks/locomo-conv","https://hanzo.ai/benchmarks/goroutine","https://hanzo.ai/benchmarks/sandbox","https://hanzo.ai/benchmarks/locomo","https://hanzo.ai/benchmarks/memoryagentbench","https://hanzo.ai/benchmarks/longmemeval","https://hanzo.ai/benchmarks/cronquestions","https://hanzo.ai/benchmarks/repobench-r","https://hanzo.ai/benchmarks/locomo-subject-scope","https://hanzo.ai/benchmarks/inference","https://hanzo.ai/benchmarks/gpqa"]} |