Same Google ADK triage agent, engine swapped: Jev 53% at 422 ms, Laya 10% at 152 ms
Madhav Sharma built one ADK triage agent over 30 labeled tickets and only swapped the decision engine. Laya was faster but far less accurate zero-shot.
Madhav Sharma built one ADK triage agent over 30 labeled tickets and only swapped the decision engine. Laya was faster but far less accurate zero-shot.
A Laya checkpoint trained on PolyAI's Banking77, the 77-intent banking support dataset, tagged for customer-support intent classification.
Cahol · Support & triage · free, Apache 2.0 base
Cahol
GitHub
Support & triage
free, Apache 2.0 base
-
Homebrew menu bar server that turns n8n Text Classifier requests into Laya typed questions in ~40 ms. Weights ship inside the app; no network, unloads when idle.
@chrisns · Support & triage · free, local · ~40 ms / question
@chrisns
GitHub
Support & triage
free, local
~40 ms / question
Spent a morning testing a small open-weights local model (Laya-MLX, fully offline on a MacBook Air, $0 per call) on real tasks: inbox triage, tagging 100 SAP decks, categorizing blog posts, and a prefilter pattern. Honest numbers in this thread.
@Raju_M_A · Support & triage · $0 / call, offline
@Raju_M_A
X post
Support & triage
$0 / call, offline
-
1,000 synthetic emails. Six folders. One local 322M Laya model running on a MacBook Air M3. ⚡ 28.6s without screen recording 🎬 97.3s while recording 🎯 65.1% accuracy against reference labels 💾 0 MB swap Everything runs locally. No cloud inference. And I’m showing the
@NURM_Dima · Support & triage · $0, local · 28.6 s for 1,000 emails
@NURM_Dima
X post
Support & triage
$0, local
28.6 s for 1,000 emails
Laya shipped right after Jev claiming to be faster for AI agent decisions. curious if it was accurate too I built a POC same Google ADK triage agent, same 30 labeled tickets, only the engine swapped. Jev: 422ms, 53% accuracy. Laya: 152ms 10% accuracy Faster not more accurate