Skip to content
JevHub

[ Built with Jev · Safety and moderation ]

jevals: evals and guardrails for agents

Runs evals and guardrails on every agent trace instead of using an LLM judge.

By Openlayer (@openlayer-ai on GitHub) ·

jevals

openlayer-ai

GitHub preview of openlayer-ai/jevals

How it uses Jev

All the checks for a trace go to Jev in one request costing a few thousandths of a cent, fast enough to run inside the agent loop.

Summary written by JevHub. Figures are the author's own; we haven't reproduced them. The project belongs to its author.

More builds

jev_antispam_bot

backmeupplz

GitHub preview of backmeupplz/jev_antispam_bot

A minimal Telegram bot that deletes spam from group chats.

spamlens

veronalabs

GitHub preview of veronalabs/spamlens

Filters spam from WordPress comments, product reviews and Contact Form 7.

Andy Gao

@instantricecook

I built a voice controlled computer-use for my mac using @typesafeai's Jev and it's INSANE how fast it is! I can dictate "open the notes app and create..." and the app opens before I even finish my sentence.

6.2Klikes on X