AI開発影響研究所 EN
← ランキング · AI関連リポジトリ

Kinneyzhang/llm-output-audit

Audit long-form LLM output for factual accuracy, hallucination risk, source quality, and actionable edit suggestions.

Python MIT GitHub ↗
★ 1
stars
100
AI関連スコア
50
個人開発度
0
AIツール痕跡

SUMMARY AI要約 by gpt-5-mini

LLM Output Audit is a portable toolkit for auditing AI-generated long-form content (research reports, docs, READMEs, blog drafts) before saving or publishing. It’s used by engineers, writers, reviewers, and agent workflows that need repeatable factual checks. It ships as a Python CLI, an stdio MCP server, and lightweight adapters for Hermes/Claude/Gemini/Codex-style agents. Key features: extracts atomic claims (DATE, NUMBER, FEATURE, REQUIREMENT, COMPAT, WORKFLOW, EVAL, CAUSAL, etc.); routes each claim to the most authoritative evidence source (GitHub, Wikipedia, arXiv, Semantic Scholar, PyPI, npm, DuckDuckGo, local LLM Wiki); verifies evidence in parallel and scores it by authority, directness, and freshness; supports audit modes (fast/spot/draft/full/auto) to balance latency vs depth; performs risk-gated consistency and conditional adversarial checks; and generates actionable edit suggestions and citations rather than binary verdicts.

DETECTED 検出されたAIスタック

このRepoのdescription / GitHub topics / READMEのAI要約に出現したAI関連キーワードをカテゴリ別に表示。各バッジは該当カテゴリの詳細ランキングへリンクします。

🧠 LLMプロバイダー (1)
Gemini
🤝 エージェントフレームワーク (1)
MCP
🤖 LLMモデル (2)
Claude Gemini

GitHub Topics

#ai-agents #audit #fact-checking #hallucination #hermes-agent #llm #verification

使用言語(バイト数比)

Python
100%

オーナー情報

アカウント
Kinneyzhang
タイプ
User
フォロワー
66

Happy hacking emacs!

日付

GitHub作成日 2026-05-09
最終Push 2026-05-09
当サイト初検出 2026-05-09
最終取得 2026-05-09 18:15

類似Repo (同じ言語のAI関連Repo)

bgzhang1/sw2api

Reverse proxy for your ai quota from the SW platform.

Python 19 AI 45
dea6cat/2b-agent

This llm Agent was created based on necessity for one that could simply use local models without making them hallucinate and keep them focus

Python 1 AI 75
Zuboy/Carbon-Cost-Optimizer-Agentic-AI

An AI agent that decides where and when to run ML training jobs to minimize cost and carbon emissions, then launches them autonomously — exposed entirely through MCP tools.

Python 1 AI 75
FuchaZ/lm-studio-vision-bridge

给纯文本 AI agent 装上眼睛——通过 LM Studio 本地视觉模型提供 MCP 图片识别服务

Python 1 AI 45
Shrutirowlo/AI-Video-Agent

AI-powered video generation agent that automates script analysis, scene planning, and video creation.

Python 1 AI 75
Shivang0/social-vision

Paste an Instagram/TikTok/YouTube/X link and Claude watches it for you — transcribes audio, reads on-screen text & visuals, explains what it's about. Local, cross-platform Claude Code plugin.

Python 1 AI 70
markusbegerow/claude-fuer-oeffentliche-verwaltung

⚠️ Experimentelle Skill-Sammlung für Digitalisierung, Fachverfahren und Organisation der deutschen öffentlichen Verwaltung (OZG, FIM, FIT-Connect, KI-Einsatz, eIDAS, BSI-IT-Grundschutz, DSGVO) – bitte testen, Issues/PRs willkommen! Keine Rechts-/Datenschutzberatung, keine verbindliche Behördenentscheidung. Keine Bürger-/Mitarbeiterdaten im Repo.

Python 1 AI 75
knowledgegut/course-distiller

把有權使用的工作坊/課程回放消化成套品牌色的步驟式學習 PDF;最後的重組交還人腦。A Claude Code skill by 知識包小腸.

Python 1 AI 45