jevegis

What Jev does in jevegis

The project describes itself this way: Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT. In the Applications category, Jev typically decides the product's core judgment, such as a document type, a moderation action or a trade direction.

Verification

Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.

Topics

• content-moderation
• guardrails
• llm-security
• nextjs
• prompt-injection
• trust-and-safety
• typesafe

How Applications projects use Jev

Complete applications with Jev inside: document classifiers, moderation bots, trading experiments, video tools and more. They show the decision layer embedded in a product rather than demonstrated on its own.

Also listed in: Security & Guardrails.

Related Jev projects in Applications

1. inboxpilotAdityaPagare619/inboxpilotSelf-hosted Gmail triage prototype using Jev urgency, category and reply-needed decisions.★ 0
   Python
2. tidyabhibansal60/tidyGmail and YouTube cleanup tool using Jev classifications with code-enforced policies and user review.★ 1
   Python
3. sortroommhoenes/sortroomBeta self-hosted IMAP mail sorter using Jev or another TypeSafe-compatible classification service.★ 1
   Python
4. qualmqddegtya/qualmA TypeScript wrapper for Jev decisions with an explicit unsure branch.★ 1
   TypeScript
5. jev-clijtsang4/jev-cliA CLI for asking Jev classification, yes/no and scoring questions over text or JSON input.★ 3
   TypeScript
6. jevsqlEugeneBoondock/jevsqlAdds Jev semantic judgments to SQLite for filtering, ranking, matching and tracking decision evidence.★ 5
   JavaScript

See all 76 Applications projects →

Where we found it

• heyjunpenn/awesome-jev