Catalog / LLM routing & guardrails
sysone-bench: Jev vs Laya on 751 byte-identical questions
Sai Dutta's independent head-to-head. Jev sweeps triage, guardrails and moderation and hits 1.000 on 5-language intent; Laya wins AG News and MNLI at $0.
Catalog / LLM routing & guardrails
Sai Dutta's independent head-to-head. Jev sweeps triage, guardrails and moderation and hits 1.000 on 5-language intent; Laya wins AG News and MNLI at $0.
Independent Jev vs Laya measurements plus a cascade: Laya decides first, high confidence executes, low confidence escalates to Jev. At a 0.60 threshold it matched Jev's 78%.
@yibie · LLM routing & guardrails · lower than pure Jev
@yibie
GitHub
LLM routing & guardrails
lower than pure Jev
-
A port of the jev-ultrafast browser agent that decides with laya-mlx instead of the hosted Jev API. DOM snapshot, executor, safety checks and inspector are the originals.
@ipenywis · LLM routing & guardrails · free, local
@ipenywis
GitHub
LLM routing & guardrails
free, local
-
Two routers behind one endpoint, measured on 180 labelled requests. Laya answers small/medium/powerful routing in one forward pass, against a GPT-5 nano router.
@glukicov · LLM routing & guardrails · free, local
@glukicov
GitHub
LLM routing & guardrails
free, local
-
Local decider for the browser-agent loop: hand it a numbered table of page controls and it picks the operation and element. Playwright/CDP driver, speaks /v1/systemone.
@ChenneyZhuang · LLM routing & guardrails · free, local, no screenshots
@ChenneyZhuang
GitHub
LLM routing & guardrails
free, local, no screenshots
-
I benchmarked Jev 1.13.0 vs open-weights Laya on 751 identical questions. Jev sweeps triage/guardrails/moderation, goes 1.000 on 5-language intent. Laya wins agnews + mnli at $0. Full data: github.com/instax-dutta/s…