shashvik/laya-security-guardrail
User repository on GitHub
- Forks
- 5
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Laya Cyber Defense Suite
A local, non-autoregressive security guardrail suite powered by Convai Innovations' Laya model, returning typed decision probabilities for security inspection. It positions itself against Jev on latency and against generative LLMs on hallucination risk.
- Stars
- 12
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- shashvik
- Last verified
- Oct 2026
Used inJev for Security & Privacy
Highlights
- Builds on Convai Innovations' Laya model (convaiinnovations/laya-typed-decisions, ModernBERT-large, 421M params).
- Its README compares a ~140ms local Laya inference against ~200ms for Jev's API roundtrip.
- Typed decision probabilities, like Jev, instead of generative prose or JSON strings.
- Runs locally on Apple Silicon MPS to avoid the latency, cost and hallucination risks of LLMs.
- License badge says Apache 2.0; GitHub metadata shows Python, created and pushed 2026-10-07.
Watch out
README and GitHub metadata reviewed 2026-10-17. The excerpt truncates inside the comparison table, so the latency figures for other rows, accuracy numbers and setup commands are not evidenced; the GitHub license field is blank despite the Apache 2.0 badge.
Questions about this entry
Short answers drawn from the linked project or page.
A local, non-autoregressive "System 1" cybersecurity intelligence suite powered by Convai Innovations' Laya model, built to remove the latency, cost and hallucination risks of using multi-second generative LLMs for security inspection.
Its README's comparison table places Jev (TypeSafe AI) and Laya in the same column family, both returning typed decision probabilities; it cites ~200ms for Jev's API roundtrip versus ~140ms for local Laya inference.
Convai Innovations' Laya, published on Hugging Face as convaiinnovations/laya-typed-decisions: a ModernBERT-large model with 421M parameters, per the repo's badges.
The badges indicate local execution on Apple Silicon MPS (PyTorch Metal). The digest does not show Linux or CUDA support, VRAM requirements or a fallback mode.
The digest positions it as a security guardrail and intelligence suite making typed decisions for security inspection, but the truncated README excerpt does not list the exact checks, classes or threat categories it covers.
Not evidenced. The README excerpt ends inside the comparison table, before any install section, so no commands, package names or configuration steps are shown in the digest.
The README displays an Apache 2.0 license badge, while the GitHub metadata in the digest shows a blank license field; verify the repository's LICENSE file before reuse.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Kubernetes admission control with a decision model, fail-closed.
Hacker News: SafeDep Gryph plus Jev checks for compromised coding-agent behavior.
2 pointsDetecting Compromised AI Coding Agents with Jev and GryphRead the thread on Hacker NewsX: Jev and Laya on security queries
X: Testing Jev for prompt injection
More Jev resources like this
A safety guardrail for coding agents (Claude Code, Codex, Cursor, Antigravity, Grok) that intercepts shell commands, script executions and file writes before they run. Its neural tier can use Liquid AI d1-3B, CLM, TypeSafe Jev cloud or pure rules; a deterministic tier blocks destructive patterns in under 0.1 ms.
Jev Tools & CLIs#community#github#security
Community
Bl4ckk01/agent-guardrailPython
Bl4ckk01/agent-guardrailPythonA proof-of-concept HTTP service for constrained decisions with a local MLX model: send text or JSON plus typed choice, score, or noul questions and it returns probabilities over the answers you declared — no generated text, no parsed model JSON.
Jev Tools & CLIs#community#github#python
Community
snellingio/system-onePython
snellingio/system-onePythonA Python sidekick that listens to a call (FaceTime, Zoom, Discord or a stream) and fires a soundboard clip when Jev thinks the moment is funny. Jev answers two questions per 1.2-second audio slice, a Noul for react-now and a Choice for which clip, at about $0.30-0.40 per hour of chatter.
Jev Tools & CLIs#community#github#python
Community
Kiggsworthy/jev-soundboardPython
Kiggsworthy/jev-soundboardPythonA 32M-parameter typed-decision model plus a Chrome extension that runs entirely on-device with WebGPU/WASM and Moonshine speech recognition. Its local server speaks POST /v1/systemone, so existing Jev clients work by changing the base URL; a benchmark table claims zero option-order flips.
Jev Tools & CLIs#community#github#chrome-extension
Community
MeharPro/GenClassPython
MeharPro/GenClassPythonA screenshot hotkey redactor for macOS, Linux and Windows that blacks out API keys, tokens, emails, phone numbers, names, internal hostnames and QR codes before the image reaches the clipboard; optional AI checks use the TypeSafe Jev API.
Jev Tools & CLIs#community#github#security
Community
brainstormity/jevsnapTypeScript
brainstormity/jevsnapTypeScriptA local decision engine for AI agents and software developers, built on the System One architecture in TypeSafe's Jev style and running fully offline through Ollama 0.35+. Ships a CLI, an MCP server and a Python library for error triage, diff review, shell guardrails and routing.
Jev Tools & CLIs#community#github#python
Community
beliciobcardoso/systemone_gatePython
beliciobcardoso/systemone_gatePythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.