ai-hallucination

Proven 2026 Multi-Agent AI Review System – Verdict-Driven Quality Control

Repo-native protocol for AI-assisted coding that enforces a simple discipline: research first, plan second, code last. Drop it into any repository to reduce wrong implementations, cut rewrite cycles, and improve decisions earlier in the workflow. Works with Cursor, VS Code, Claude Code, and Windsurf across Claude, GPT, Gemini, Grok, and DeepSeek.

29 .mdc architecture rules that prevent AI coding assistants from hallucinating insecure auth, deprecated imports, and broken Next.js 15 patterns. Built for Cursor Agent and Claude Code.

🔍 Real-time AI hallucination detector — Chrome extension that fact-checks every sentence from ChatGPT, Claude, Gemini & Copilot using Wikipedia, PubMed, and Groq AI

🔁 double-check — force your AI to review its own work and catch the bugs & hallucinations it missed the first time. A Claude Code self-review skill. 让 AI 复盘自审,揪出它漏掉的 bug 和幻觉

Stop your AI from hallucinating its own history. Session discipline for Claude Code — the problem everyone has but nobody else is solving mechanically.

AI Content Guard 2026: Adversarial Fact-Check Gate for Error-Free Code & Copy

Verify BibTeX references against OpenAlex & CrossRef to detect errors and AI hallucinations

Physical Layer Linter — MCP server that validates RF link budgets, Shannon capacity, and noise floors against hard physical limits

[Veracity] Dual-LLM hallucination defense — adversarial verification with Localization Gap detection for Arabic knowledge

Open Council: Claude Code skill for multi-agent AI quality control. Ten specialist employees draft the work. Ten industry-veteran board members review it. You see one verdict. Anti-sycophancy, anti-hallucination, multi-perspective review.

A 5-layer adversarial quality gate for Claude Code. Catches factual errors, score inflation, and buried conclusions before your AI output ships.

Stop AI Agent Drift, Session Amnesia & Ghost Continuity. Hermes skill implementing the ContinuityKit protocol — heartbeats, session snapshots, and RELAY cross-session tracking.

Fail-closed citation verification against CourtListener. Catches fabricated cases, fabricated quotes, and pincite errors in US legal writing.

TriTai 三才 - 零 Token AI 防幻觉引擎，基于太极哲学的 LLM 输出验证系统，集成 WFGY 规则引擎和知识图谱

如何保障人的权利不被AI侵犯？

Watchdog — AI session immune system for Claude Code. Detects stuck loops, hallucinations, task drift & context decay. Like /btw but for session health.

Open-source AI reasoning auditor for legal citations. Verifies existence, quote accuracy, and logical coherence against primary sources.

AI Alignment through the Eyes of an Industrial Designer

This is a SAMPLE of how roles can be used to give the LLM a sense of self and to help it identify the users purpose and ensure greater governance over actions