beulah0/Multi-Agent-Fact-Check-System
Multi Agent system where two LLM agents argue opposite sides of a claim, a third agent judges based on retrieved evidence, and a final verdict is issued with confidence score. LangGraph is used for multi-agent orchestration. Applied it to detect misinformation on Indian news.
SUMMARY AI要約 by gpt-5-mini
Multi-Agent-Fact-Check-System is an open-source pipeline that evaluates the truthfulness of user claims (tested on Indian news) by combining retrieval and multi-agent LLM reasoning. It is intended for developers, researchers, fact‑checkers and journalists who need automated evidence-based verification. Key features: retrieval-augmented generation using hybrid retrieval (live web search via Tavily + FAISS vector search over an Indian news corpus), three LLM agents (Advocate supports the claim, Refuter challenges it, Judge issues a final verdict with confidence), LangGraph for orchestration, and a Gradio UI that emits structured JSON (verdict, confidence, reasoning, sources). Requires Groq LLM and Tavily API keys; FAISS index must be built before running. Modular code (agents, retriever, ingestion) enables extension and evaluation work.
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。
使用言語(バイト数比)
AI関連と判定した根拠
AI関連スコアは4つの箇所それぞれにAI関連キーワードが現れるかを判定し、該当した配点を合計したものです。 算出方法の詳細
合計 AI関連スコア: 75 / 100
同じ言語のAI関連Repoの中での位置
当サイトが追跡している Python 製Repoは 19,340件 (うちAI関連スコア40以上は 15,086件)。 このRepoより スター数が多いのは 3,410件 (上位 17.6%)、 AI関連スコアが高いのは 907件 (上位 4.7%) です。
オーナー情報
日付
| GitHub作成日 | 2026-05-23 |
| 最終Push | 2026-05-23 |
| 当サイト初検出 | 2026-05-23 |
| 最終取得 | 2026-09-28 16:25 |
類似Repo (同じ言語のAI関連Repo)
A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。
experientiallabs/experientialExperiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.
AminBlg/SimpleEnglishAgent skill: make LLMs write docs in ASD-STE100 Simplified Technical
Sophomoresty/gemini-web2apiConvert Google Gemini web into OpenAI-compatible API. Zero auth, cross-platform, single file.
HarnessRouter/harnessrouterHarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
Alisa0808/vox-directorTurn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.
coji/natural-japanese仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。
ray-r-ren/agent-apprenticeshipThe living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.