DEDUPEDWhat do you want to do?
3 use cases
-
Route support tickets by department, urgency and churn risk
Ask Laya typed questions about each ticket and get a department, an urgency score and a churn probability.
View prompt
Using NandhaKishorM/laya, write a script that reads tickets from <source>, asks a department choice (billing, technical, other), an urgency score and a churn_risk noul for each, and writes the answers to a CSV. Flag any ticket where churn_risk is above 0.7.
-
Triage customer messages in 100+ languages with one model
Let the Router send non-English text to the multilingual checkpoint and get the same structured answers.
View prompt
Using NandhaKishorM/laya's Router, classify these customer messages in their original languages by department and urgency: <messages>. Print the routing model for each, and use model multilingual with max_len 8192 for any message longer than a page.
-
Fine-tune Laya on your own decisions for higher accuracy
Use the fine-tuning notebook or Apple Silicon script to train on decisions from your domain.
View prompt
Help me fine-tune NandhaKishorM/laya on my labeled decisions in <file> using the README's Fine-tuning notebook flow. Build the dataset, train, calibrate and evaluate, then report accuracy against the base English checkpoint on a held-out split.
Quick start with Laya
- Check you have what it needs: Python 3.10 or newer; pip or uv; A GPU is optional; checkpoints download on first use.
- Open NandhaKishorM/laya on GitHub and read the README and license.
- Install with
python -m pip install laya - Create a Router; it downloads a checkpoint on first use
- Define questions as in the Quickstart: a choice for department, a score for urgency and a noul for churn risk
- Call
router.predict(state, questions)on each ticket text
These steps come from our top use case, Route support tickets by department, urgency and churn risk, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for NandhaKishorM/laya
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forDevelopers and support or ops teams who need fast, cheap, structured decisions such as routing, urgency and churn risk instead of calling a chat model.
- Why it is hot34k stars, launched 38 days ago, picked up by one AI source we track
- LanguagePython
- Sourcegithub.com/NandhaKishorM/laya · Back to Hot repos
Requirements
- Python 3.10 or newer
- pip or uv
- A GPU is optional; checkpoints download on first use
- Optional extras: laya[serve], laya[mcp], laya[langchain] and others
Add this badge to your README
Maintain Laya? Show readers where to find these use cases. 
Markdown
[](https://dedupedai.com/use-cases/nandhakishorm-laya/?utm_source=github&utm_medium=badge&utm_campaign=NandhaKishorM-laya)
HTML
<a href="https://dedupedai.com/use-cases/nandhakishorm-laya/?utm_source=github&utm_medium=badge&utm_campaign=NandhaKishorM-laya"><img src="https://dedupedai.com/badge/NandhaKishorM/laya.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Laya
What is Laya?
Laya is a multilingual, non-autoregressive decision engine. It answers typed questions (choice, score and noul yes/no probabilities) over any text, email, ticket or JSON document in a single forward pass, about 33 ms per question on a T4, with no text generation to parse. A Router picks between an English, a multilingual (100+ languages) and a typed-decisions checkpoint per request. It is an open-source project on GitHub: https://github.com/NandhaKishorM/laya.
How do I use Laya?
Install with python -m pip install laya; then create a Router; it downloads a checkpoint on first use; Define questions as in the Quickstart: a choice for department, a score for urgency and a noul for churn risk. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Laya for?
Developers and support or ops teams who need fast, cheap, structured decisions such as routing, urgency and churn risk instead of calling a chat model.
What can I do with Laya?
3 use cases so far, for example: Route support tickets by department, urgency and churn risk; Triage customer messages in 100+ languages with one model; Fine-tune Laya on your own decisions for higher accuracy. Each has steps and a copy-paste agent prompt.
What do I need to run Laya?
Python 3.10 or newer; pip or uv; A GPU is optional; checkpoints download on first use; Optional extras: laya[serve], laya[mcp], laya[langchain] and others.
What are alternatives to Laya?
Other hot AI repos in Work and operations: Solidcraft, Meetcap, Start Lux Decision, Agenticos, Astr Bot.
Is Laya safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.