← 최신 프로덕트

jevals

replacing LLM judges with typed Jev decisions. Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.

오픈소스

110 스타 · GitHub외부 사이트

github.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. BlitzGraph

    blitzgraph.com

    Supabase for graphs, built for LLM agents

    Hacker News15점

  2. Proval

    github.com

    Self-hosted code review agent for GitLab, Forgejo, and GitHub

    Hacker News13점

  3. JevBench

    benchmarkheaven.com

    a reproducible benchmark for typed decision models

    Hacker News154점

  4. Jevcrawl

    github.com

    A web crawler for AI agents with no LLM in the crawl loop

    Hacker News21점

  5. Forge

    github.com

    Guardrails take an 8B model from 53% to 99% on agentic tasks

    Hacker News687점