Enso routes. Zen writes. Kai decides.

Kai first: typed decisions against Laya and Jev, on the same questions. Then Enso and Zen, the platform they run on, memory, and the rest of the suite, each result beside the baseline it was measured against.

Enso, Zen, and Kai

Three models on one call path. Enso takes every call, in every modality, and hands it to the model that should answer it: Zen to write, Kai to decide, or another frontier model.

Kai, against Laya and Jev.

The top mean accuracy across 11 application suites.

Laya is the upstream kai-1 weights, served natively. Jev is typesafe/jev-1.13-20260917 through OpenRouter.

Platform, agents, and sandboxes

What an agent costs at rest, what a live one costs to wake, and what a sandbox costs to start.

A live agent here is a goroutine: it shares one address space with every other, and nothing about it is an isolation boundary. Code that has to be isolated gets a microVM, which boots in 309 ms on an M-series laptop. The goroutine timings are the median of one pass on an Apple M4 Max, 16 cores. Every figure here is transcribed from the harness's README rather than read from a run file, and each page names the command that prints it.

Memory and retrieval

What a memory finds in a long conversation, and what a reader does with it. Each panel is one metric, the baseline and Hanzo on the same data, the same embedder and the same cut-off, drawn on one scale.

Knowledge graph

Point-in-time questions over facts that begin and end, against another temporal store on the same data. On the CronQuestions types the harness covers, the Hanzo graph answers 99.88% and Semantica 99.88%; what differs is the price of a question.

Code

Cross-file retrieval in a repository, scored apart from generation. Typed links are regular expressions over imports, definitions and identifiers; no model reads anything in that row.

Every benchmark

Grouped in the order the board runs: our models, the platform, memory, then the rest. Each page carries its protocol, its tables, and — where a public command regenerates the tables — that command.

The rest of the record

Finding the evidence is not answering from it. On LoCoMo, multi-hop ALL@20 goes from 18.8 to 37.5, but the answers one reader writes from it move from 36.3 to 39.0 token F1 over 208 questions, inside the baseline's interval of [31.5, 40.9] — and the annotated gold turns reach only 50.8. LoCoMo

MemoryAgentBench stops at 262k multi-hop. 67.0 is where the typed search stands there. Most of the misses want an earlier version of a fact that a later line overwrites, and nothing in the haystack says which edit the question follows. MemoryAgentBench

The engine is slower than cosine. On LongMemEval its retrieval takes 1.96 ms at the median against 0.20 ms, and session recall is not answer accuracy. LongMemEval

The code rows compare generators; they are not a held-out result. No configuration was frozen on dev before the test split ran, and on cross-file-random the full combination scores 30.2 R@1 against 31.2 for dense retrieval with typed links alone. RepoBench-R

Decode trails llama.cpp on every backend measured, and prefill loses on Metal, ROCm, and Vulkan at one prompt length or more. The inference page has every cell with its interval. Inference

GPQA-Diamond is the router’s published board. It lives on its own page, with every tier and the models Enso dispatches to. GPQA-Diamond