User repository on GitHub
Open-source Discord moderation bot powered by Jev, TypeSafe's decision model.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Tools & CLIs
Jev-Mod (i098)
An 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.
- Stars
- 0
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- i098
- Last verified
- Oct 2026
- Languages
- TypeScript
- Capabilities
- Open sourceRequires API key
Highlights
- Jev rules detect spam, phishing, harassment, hate, threats and explicit sexual text; actions are log, delete, or delete plus timeout.
- Non-AI local filters block phrases and limit mentions, and channel or role exceptions bypass the automatic rules.
- Hosted flow: sign in with Discord, add the bot where you have Manage Server, set your TypeSafe key under Server settings, then enable Protect server.
- Commands include /jevmod status and /jevmod pause, and an activity view lets you search, filter and review recorded cases.
- MIT licensed; no bot token or hosting account is needed for the hosted service, per the README.
Watch out
README reviewed 2026-10-17 from the round-eleven capture, which is truncated after the moderation table: pricing, data retention, self-hosting instructions and the linked docs/guide.md are not in the digest.
Questions about this entry
Short answers drawn from the linked project or page.
An open-source Discord moderation bot powered by Jev, TypeSafe's decision model. It is offered as a hosted service with a dashboard at app.jevmod.us, while the code itself is MIT licensed on GitHub.
The server owner defines rules, and Jev detects spam, phishing, harassment, hate, threats and explicit sexual text. Matched messages can be logged, deleted, or deleted with a timeout applied.
Sign in to the dashboard with Discord, add Jev-Mod to a server where you have Manage Server permission, add your TypeSafe key under Server settings, set your rules, test in Monitor only mode, then enable Protect server.
Yes, per the README's get-started steps: you paste it under Server settings, API key. The captured excerpt does not say whether that key usage is metered or priced.
Yes. Local filters block phrases and limit mentions without AI, exceptions let you exclude channels and roles, and commands like /jevmod status and /jevmod pause let you control the bot directly.
The repository is open-source under MIT, and the README says no bot token or hosting account is needed for the hosted service, but self-hosting steps are not in the captured excerpt, so only the hosted path is documented here.
The digest truncates the README after the moderation table, so pricing, data handling, case retention and the docs/guide.md contents are unknown. The repository has 0 stars and no documented adoption.
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
Moderation for communities and apps, powered by Jev: every message gets a probability for spam, scam, harassment, nsfw, doxxing and more, plus rules in plain English. Thresholds and actions are yours, and flag-only is the default.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
ohernandezdev/jevmodPython
ohernandezdev/jevmodPythonA guard that stands outside an LLM agent and uses TypeSafe Jev to score both incoming prompts and proposed actions, turning the score into a block, a question, or a pass; in the README's Gandalf test it rejected 17 of 21 published injection prompts before send.
Jev Tools & CLIs#community#github#security
Community
JamesANZ/JevPromptShieldTypeScript
JamesANZ/JevPromptShieldTypeScriptAn installable Electron email client for Windows, with a macOS build target, that sorts mail with Jev: one call per message classifies it into Important and Other and rates relevance. TypeSafe, Vercel AI Gateway and OpenRouter endpoints all serve Jev; local sorting works without any key.
Jev Tools & CLIs#community#github#email
Community
screen-devs/aggregate-mailTypeScript
screen-devs/aggregate-mailTypeScriptA self-hostable Discord auto-moderation bot written in Go and powered by Jev, TypeSafe's System One model: it reads every message, asks Jev whether it breaks server rules, and a deterministic policy turns the answers into flags, deletions or timeouts.
Jev Tools & CLIs#community#github#go
Community
glazk0/shugoGo
glazk0/shugoGoA self-hosted multi-bot group chat: rooms hold people and bots, mentions wake specific bots, and with no mention Jev scores who should reply while a daemon on your own machine runs each turn through Pi.
Jev Tools & CLIs#community#github#typescript
Community
nikuscs/orbsTypeScript
nikuscs/orbsTypeScriptA Claude Code plugin from cth9191 that gives compaction to Jev: it keeps tool output that is still needed word for word and moves the rest to a drawer file, taking 0.43 to 0.74 s instead of about 35 s on one 591,489-token session. A fork of fast-jev-compaction.
Jev Tools & CLIs#community#github#claude-code
From 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.