madewithlaya

Catalog / Support & triage

0040X posts

A morning of real tasks on Laya-MLX: inbox triage, 100 SAP decks, blog categories

FrontierMind tested the offline model on a MacBook Air at $0 per call on inbox triage, tagging 100 SAP decks, categorizing blog posts and a prefilter pattern.

Open source ↗ x.comcost$0 / call, offlinetime-

Also filed under Support & triage

  1. 0113

    Laya fine-tuned on Banking77 for customer-support intent classification

    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

  2. 0068

    Laya Serve for macOS: a menu bar app with an OpenAI-compatible endpoint for n8n

    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

  3. 0041

    Same Google ADK triage agent, engine swapped: Jev 53% at 422 ms, Laya 10% at 152 ms

    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

    @MadhavSz · Support & triage · free, local (Laya) · 152 ms (Laya) vs 422 ms (Jev)

  4. 0039

    1,000 synthetic emails into six folders with local Laya on a MacBook Air

    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