aionedge.jev-sentinel
A guardrail for coding agents built on Jev that checks tool calls, tool outputs, and agent replies for prompt injection, missing approvals, and leaked secrets, shipped as one shared rule set across a Pi extension, a Claude Code plugin, and a Codex CLI plugin — built on the premise that a README telling an agent to `curl | sh` is just more text the model needs to be checked against.
- GitHub stars
- 9 as of 2026-09-22
- Forks
- 1
- Language
- TypeScript
- License
- MIT
- Created
- 2026-09-19
- Last updated on GitHub
- 2026-09-20
- Added to AionEdge
- 2026-09-22
What Jev does in jev-sentinel
Listed on awesomejev.com; not yet independently verified against the repository.
Verification
Integration not confirmed yet. This repository is public and listed by the community source below, but we have not yet located the code that calls Jev. Check the repository before relying on the integration, and tell us through the submission form if you find it.
How Community (New) projects use Jev
Recently discovered community projects that mention Jev. They were found through public lists and submissions and are waiting for a closer look, so treat each one as a lead worth exploring rather than a confirmed integration.
Related Jev projects in Community (New)
- awesome-jevckaraca/awesome-jevA curated 'awesome list' cataloguing tools, integrations, and experiments built around Jev, TypeSafe AI's fast typed-decision model.★ 9
Python - fable-jevimmamdouhaboammar/fable-jevA layer combining TypeSafe's Jev with get-fable's deterministic lifecycle engine to give autonomous coding agents sub-100ms 'reflex' decisions for the small, frequent choices that don't need full model reasoning.★ 9
TypeScript - jevcachekushals256/jevcacheAn OpenAI-compatible local cache proxy that asks Jev whether a new request has the same intent as a previously cached one, skipping the expensive downstream LLM call when it does.★ 9
TypeScript - jevflowmawfyy/jevflowA TypeScript library that treats probabilistic AI decisions as a composable backend primitive, letting developers define typed judgments (yes/no, score, choice) with explicit thresholds and deterministic policy layered on top, defaulting to TypeSafe's Jev but built to be provider-agnostic.★ 9
TypeScript - jev_project_contextpoiuyjie/jev_project_contextAn evidence-first, long-term memory skill for AI coding agents on research projects, keeping every claim traceable back to the evidence that produced it and every session resumable without having to reconstruct what happened, with optional Jev decision-model layers built in — available in English and Chinese.★ 9
Python - jev.nucablehead/jev.nuA module for the Nushell shell that wraps TypeSafe's Jev API, letting you pipe text through typed questions and get back numeric, filterable, sortable answers directly in shell pipelines.★ 8
Nushell