Organization repository on GitHub
Opt-in text and image moderation for Discord, powered by Jev, with reusable moderation packs. Formerly Jev Image Guard.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Integrations & Adapters
TypeCheck
An image-only Discord moderation bot powered by Jev, formerly Jev Image Guard. It checks exact normalized-image hashes first, sends the remaining references to Jev, and lets a policy engine choose the action.
- Stars
- 0
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- Jev-Engineering
- Last verified
- Oct 2026
- Languages
- TypeScript
- Capabilities
- Open source
Highlights
- Image-only moderation for Discord: members post attachments, and exact normalized-image hashes are checked before Jev sees the remaining references.
- A policy engine chooses the action, and an embedded management Activity exposes cost and usage reporting for a guild.
- Cost analytics report guild-scoped attempts, input tokens and estimated Jev spend; missing rates produce coverage warnings, not a bill.
- Version 0.1.0, described as an implementation candidate dated October 15, 2026; existing installations require forward migration 002.
- Formerly called Jev Image Guard; MIT licensed, created 2026-10-16, last pushed 2026-10-17, zero stars at sweep time.
Watch out
README reviewed 2026-10-17; the excerpt cuts off mid-sentence while describing the bot loop, and the README stresses that no deployment or production acceptance is implied. Cost figures are estimates that depend on rates administrators supply.
Questions about this entry
Short answers drawn from the linked project or page.
A Discord moderation bot that handles images only. A member posts an attachment, compatible exact normalized-image hashes are checked first, Jev compares the remaining references, and a policy engine chooses the action.
Jev performs the image comparison once identical normalized-image hashes have been ruled out; the README describes the bot as powered by Jev, and the cost report tracks estimated Jev input-token spend per guild.
Guild-scoped attempts, reported input tokens and estimated Jev input-token spend, with retries, verification and credential tests tracked separately. Administrators supply revisioned rates; missing rates produce coverage warnings, never a made-up total.
Not according to its own README: it is version 0.1.0, labelled an implementation candidate dated October 15, 2026, and it explicitly says no deployment or production acceptance is implied.
TypeCheck is the new name of the same project: the README says it was formerly Jev Image Guard and keeps the image-moderation-for-Discord purpose. Existing installations require forward migration 002.
It is published by the Jev-Engineering organisation under the MIT license; GitHub metadata shows a TypeScript repository created 2026-10-16 and last pushed 2026-10-17, with zero stars at sweep time.
The project describes itself as image-only moderation for Discord. Nothing in the captured text covers text moderation, and the embedded management Activity is for administration and cost reporting.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: Building a contextual brand-safety scorer on Jev from scratch.
X: A website slop detector that checks 35 tells in 243 ms
X: Breaking, golden nugget, or slop
X: A filter for reply-guy comments
More Jev resources like this
An opencode plugin (also for pi and Claude Code) that puts every bash command in front of a System One decision model before it runs: a small model scores destructiveness, secret leakage, and your repo's GUARDRAILS.md policy and blocks bad calls.
Jev Integrations & Adapters#community#github#opencode
Community
berget-ai/guardrails-mdTypeScript
berget-ai/guardrails-mdTypeScriptCloudflare Worker that asks Jev on Workers AI for literal profanity in text or usernames and, for usernames, a second Noul for phonetic or look-alike disguises. The threshold and max policy live in Worker code, with OpenAPI docs generated via chanfana and Hono.
Jev Integrations & Adapters#community#cloudflare-workers#moderation
Community
4rays/profanity-checkerTypeScript
4rays/profanity-checkerTypeScriptAn open-source Discord moderation bot powered by Jev. Owners sign in to a hosted dashboard, add the bot, supply their own TypeSafe key, test in Monitor only mode, then let Jev rules log, delete or time out spam, phishing, harassment, hate and threats.
Jev Tools & CLIs#community#github#typescript
Community
i098/jev-modTypeScript
i098/jev-modTypeScriptAn unofficial Claude Code plugin that checks 'done' claims and small judgement calls with TypeSafe Jev and keeps receipts: its done-gate can reject 'all tests pass' and ask for a real check, so evidence beats eloquence.
Jev Integrations & Adapters#community#github#claude-code
Community
ismaildasci/claude-refereeTypeScript
ismaildasci/claude-refereeTypeScriptAn auto-mode plugin for the Pi coding agent that classifies shell commands before they run: built-in rules decide most calls, and Jev (hosted) or Kev and Laya (local, CPU, offline) route the rest to run, confirm, or block.
Jev Integrations & Adapters#community#github#pi
An LLM-agnostic guardrail API built on Jev: it checks prompts and responses against YAML policies and returns PASSED, BLOCKED or FAILED. It sits between your app and any LLM provider, so guardrail decisions do not depend on the provider you call.
Jev Integrations & Adapters#community#github#guardrails
Community
alpkeskin/jev-guardrailGo
alpkeskin/jev-guardrailGoFrom 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.