#fact-checking

Evidence-grounded research agent for Claude Code & Codex: every claim gets a confidence rating + source-family tag, and adversarial gates block unsupported claims before they reach your report. Ships with a multi-model dispatcher.

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

Offline semantic search for everything on your disk - documents, code, PDFs, scanned images (OCR), video by the second. 100% local AI: hybrid RAG with keyword + vector + rerank, no API key, no cloud. Desktop app + 24 MCP tools for Claude Code, plus a multi-engine web researcher that quotes sources verbatim. 本地离线多模态语义检索

An AI-powered Fact-Checking Agent built with Python, Gradio, and Google GenAI.

Backend-agnostic black-box hallucination & RAG-faithfulness detection for LLMs — Probabilistic Certainty & Consistency (arXiv:2601.02574). Works on MLX / OpenAI / vLLM via token logprobs; no model internals, no training.

Stop Claude from lying to you. A Claude Code skill that fact-checks every claim against real sources — code files, live docs, web search — and flags anything it can't confirm.

Deterministic fact-checker for AI coding agents — verify an agent's claims about its own work against the real code, git diff & logs. Local MCP server, cited verdicts, refuses to bluff.