LLM output verification with decision models

Checks whether each cited paper supports its citing sentence: code fetches papers, Claude proves a quote, Jev scores it, a human decides.

Published Jev client and claim check from the Fake/Real evidence-review site, where Jev filters sources and judges each claim.

Zilliz semantic cache for LLM queries, listed for a Jev evaluator that uses Noul checks to decide whether a cached answer can be served.

Agent observability platform that finds and fixes agent failures, with an optional Jev preclassifier for conversation checks.

Video summarizer that ties every line to its second; Jev checks each summary sentence against what was said, with numbers checked in code.

Claude Code Stop hook that checks an assistant's claims against what it actually read this session using Jev, blocking unsupported ones.

Local MCP bridge letting Codex hand drafting to Gemini via a Google AI Pro quota, with Jev checking drafts against explicit criteria.

SRT subtitle translator that translates with any OpenRouter LLM and asks Jev a review Noul per line to flag defects before export.

Evidence-first experiment-memory skill for coding agents, with an optional Jev audit layer that checks provenance and claim support.

WeChat reply assistant fork: DeepSeek drafts three replies, Jev pre-judges, reviews and ranks them; auto-send is cancellable.

jevctl: Node CLI for typed Jev judgments (verify claims, screen agent hijacks, classify) with exit codes for CI gating.

Hermes plugin that asks Jev to review risky plans, check claims against sources, and judge whether a task is really finished.

Claude Code plugin that checks every reply and file edit against your CLAUDE.md rules with one Jev yes/no per rule.

Editorial QA tool where Jev judges per fact whether an edit preserved the original, with a confidence gate and human review fallback.

Claude Code plugin with nine Jev-judged gates for rules, scope, intent, completion and claims that escalate but never approve.

MCP server giving coding agents typed judgment tools (verify, screen, rerank, gate, score) backed by Jev, with auto/review/escalate policy.

GitHub Action that reviews repository files against your yes/no questions with Jev and passes only when every answer meets its threshold.

Typed-decision accuracy layer for RAG: six checks for intent, relevance, clarification, sufficiency, grounding and caveats.

Small stdio MCP server with ask, rank and verify tools backed by Jev, a local event log and installers for several agent harnesses.

Unofficial Python adapter that brings Jev verification, classification and scoring into the Mellea framework as Requirements.

Permission-aware document library using Jev or Cloudflare Clef for hierarchical search, passage scoring and automatic filing.

Go CLI that gives coding agents Jev-powered lookups and calibrated yes/no or choice verdicts instead of reading whole files.

Local memory for coding agents that stores verbatim quotes and has Jev grade memory lines as keep, stale, wrong or unsupported.

Python library that replaces hard-coded RAG thresholds with calibrated decisions for stopping, chunking, selection, abstention and caching.

Semantic test matchers for Vitest and Jest that ask Jev whether output satisfies a plain-English expectation and threshold the probability.

Jev-powered adversarial or advisory reviewer for the omp coding agent, plus a typesafe_ask tool, plan/stop gates and context compaction.

pytest plugin for semantic assertions on LLM output, asking Jev whether plain-English claims hold with a 0.8 probability bar.

Prose linter for AI writing tells: regex handles 18, Jev judges 15 as Nouls in one call, shipped as a Claude Code Stop hook.

Unofficial Codex and Claude Code MCP plugin giving agents bounded Jev tools for routing, ranking, extraction, verification and judging.

Small Python demos of Jev: parallel Noul ticket checks with measured speedup, and a three-way Choice citation and claim checker.