logoSeailife
  • Submit Project
  • Pricing
  • Blog
Sign inSign up
Sign in
logoSeailife

© 2026 Seailife. All rights reserved.

Built with Open Launch - The first complete open source alternative to Product Hunt.

For AI agents: llms.txt

Powered by Open-LaunchPowered by Open-Launch

Discover

  • Trending
  • Categories
  • Submit Project

Resources

  • Pricing
  • Sponsors
  • Blog

Legal

  • Terms of Service
  • Privacy Policy
  • Submission Guidelines

Connect

  • [email protected]
Laya Logo

Laya

Artificial IntelligenceMachine LearningOpen Source
Visit
0 upvotes

Laya is an open-source model that reads a message and answers the questions you set, such as which team should handle it, without writing a reply.

A ticket, three questions, no essay

The project's own quickstart uses one billing email: "Hi, we were billed twice for March. Please refund the duplicate today or we will cancel our plan." You hand Laya that text plus the questions. It does not draft the refund reply.

  • Which department: billing, technical, or other. On this email the documented answer is billing.
  • How urgent, on a scale you define, such as not urgent, soon, or blocking.
  • A yes-or-no probability, here "does the user threaten to cancel." The field is a probability, not a sentence.

Three checkpoints, and a router picks one

  • English, 421M parameters, 512-token context. The router uses this for the billing email above.
  • Multilingual, 322M parameters, for 100+ languages. The same department question in Hindi or Spanish is documented as routing here.
  • A third checkpoint fine-tuned on four workflows: invoices, security incidents, customer service, and agent traces.
  • Install with pip install laya. Apache 2.0. Weights are on Hugging Face under convaiinnovations/laya, and only the checkpoint you ask for is downloaded.

The base checkpoint is a starting point

On the project's typed-decisions benchmark, the base English checkpoint scores 0.362 and the fine-tuned one scores 0.766. Those are Laya's own numbers. The README also says one question takes about 33 ms on a T4, and about 7.2 ms per question when batched. That timing is their measurement, not an independent test.

Laya Logo

Laya

Ready to try it? Open the official website.

Visit Laya

Comments

Submitted by

Seailife

Seailife

Launch Date
2026-09-30
Platform
other
Pricing
free
Socials

Sponsors

Become a Sponsor

Get your brand featured here

Similar tools

  • Cloudflare Clef logo
    Cloudflare Cleffreemium

    Cloudflare Clef is a decision model for developers classifying records, routing requests and choosing the next step in an AI workflow.

  • MOSS-Image logo
    MOSS-Imagefree

    MOSS-Image is OpenMOSS's open image model that paints from a sentence or from a JSON note of where each word and object should sit.

  • Microsoft-Decision-1.1 logo
    Microsoft-Decision-1.1paid

    Microsoft-Decision-1.1 helps software route support tickets, sort documents into categories, and decide which requests to handle first.

  • LFM3 logo
    LFM3free

    LFM3 is Liquid AI's open-weight family of small models for text, vision, audio, and decisions, for people who want to run one on their own device.

  • HeyGen logo
    HeyGenfreemium

    Create AI videos from your ideas using HeyGen. Input text, image, or audio to create complete videos with narration, captions, visuals, and animations.

More in Machine Learning

Mentioned in

  • Laya vs Jev: Local Decision Model or Hosted API?