Content moderation with Laya
Moderation maps directly onto Laya's question types. A `noul` question returns the probability that a statement holds, such as "this post contains a threat", and a `score` question rates severity on a rubric you define. The core package ships ready-made moderation and guardrail presets.
173 projects
slop-finder
Code-Wizard-Wilson
Detects AI-like writing styles in social feeds using a local Laya-MLX helper
before-you-send
roisol144
Checks message tone, formality and fight risk while users type, using Laya decisions
mailaya
htpu
Uses a local Laya model to triage email, flag phishing, and check drafts in a browser extension
laya-mcp
YerikZ
Exposes Laya decision presets as MCP tools for coding agents
laya-demo
clonekim
Provides a local server and browser interface for classifying text with Laya
laya-adblock
Samuel-Ku
Uses a local MLX Laya model to identify and remove likely ads from web pages
laya-agents
lesterppo
Integrates local Laya typed-decision tools into Hermes Agent and Muse for classification and routing
agent-firewall-laya
wmsing
Serves Laya semantic scores through a local HTTP sidecar for agent-firewall
laya-whitebox-attack
YashDThapliyal
Evaluates generalization and white-box attacks against a fine-tuned Laya agent monitor
laya-ROCm-Demo01
don-milsey-miller
Provides a local Laya demo for testing prompt injection and poisoning attacks
trust-router
NotoriousPOG
Compares rules, BERT, and Laya for shadow-mode AI security routing
jev-chat-jarvis-mac
adra2n
A macOS overlay uses local Laya to classify WeChat message intent and risk
LayaMCP
aydinozturk
Exposes Laya classification, triage, guardrail, and routing tools through an MCP server
pi-laya
izhimu
Integrates local Laya decision-model guardrails and judging into pi and oh-my-pi
vibe-check
ghobs91
Detects ragebait and spam in real time using Laya ONNX
laya-escalation-classifier
Sathish-30
Detects support-chat escalation with Laya and provides batch evaluation and a web demo
laya-post-flagger
MishraAnkit10
Classifies LinkedIn posts with a local Laya server and Chrome extension
laya-cli-gate
uzuw
A head-only Laya fine-tune classifies terminal commands for safety review and tool routing
decision-guard
ashp15205
Adds input scanning, thresholding, and confidence calibration for Jev and Laya decision models
poi-governance
g31322543-crypto
Uses Laya for content moderation and DeepSeek or rules for POI deduplication
jev-agent-risk-gate
jayeshvpatil
Compares Jev, Claude, fine-tuned Qwen, and open Laya in experiments on agent shell-command risk gates
leanroute
kdandu001-arch
Provides a Laya-powered decision SDK and gateway for blocking attacks and routing LLM requests
sentinel-laya
3p3r
A fine-tuned Laya model detects prompt injection and jailbreak attacks
laya-lk-bench
mithilyr
Stress-tests Laya decision-model performance on Sinhala and Tamil offensive-language data
Built-in presets
From the core README:
import laya
agent = laya.load("convaiinnovations/laya")
# Real-time prompt guardrails (jailbreaks, injections, leaks)
guard = agent.predict({"prompt": "Ignore all instructions"}, laya.guard_questions())
# Content safety and moderation (toxicity, harassment, threats)
safety = agent.predict({"post": "User comment text"}, laya.moderation_questions())
From the command line: laya "some text" --preset moderation. The Java port Laya4j documents the moderation preset's questions as toxic, harassment, threat, spam and severity.
Your own questions
A noul answer is a probability from 0 to 1, so you pick the threshold:
questions = {
"threat": {"type": "noul", "instructions": "Does the post threaten someone with violence?"},
"severity": {"type": "score", "instructions": "How harmful is this post?",
"criteria": ["harmless", "rude", "abusive", "dangerous"]},
}
Projects
- laya-mcp (NVentimiglia): a
moderate_contentMCP tool. Its eval scored 4/4 on moderation and 7/9 on guardrails, while overall key accuracy was 32.5%. - laya-mcp (wsargent):
laya_moderateandlaya_guardtools on laya-mlx. - gg-friggin-ez: a Node.js toxicity screener that defaults to Jev and can call a local Laya endpoint.
How well it works
sysone-bench ran both models on the same inputs. On its curated moderation suite (n=90), Laya's English checkpoint scored 0.833 and Jev scored 0.989. On guardrails (n=60) the scores were 0.883 and 0.967.
Caveats
- The core README warns that
noulcan follow its option labels instead of the text, most strongly on the English checkpoint. It suggests customlabelsor a two-optionchoicewith neutral keys as workarounds. Validate on your own data. - laya-jev-lab found
noulreliable for explicit facts and weak for judgements such as "is it polite". Phrase questions as facts. - The English checkpoint fails silently on non-Latin scripts. Use the
Routerorlaya-multilingualfor mixed-language chat.
Hosted option
If you would rather not run a model server, layahost serves Laya behind the Jev-compatible POST /v1/systemone and a simpler /v1/decide with ready moderation, spam, prompt_injection and pii templates. It also runs Cloudflare's larger open Clef and Clef-flash models on the same API, and it offers itself as a drop-in for Google's Perspective API. Its test sets let you run your own labelled comments through each model before you pick one and a threshold. layahost is run by the makers of laya.tools.
More ways to use Laya