Fact-checking system for textual and visual inputs.

Detect hallucinations in LLM responses. Verify every claim against source documents using hybrid STS + NLI. Works with LangChain, LlamaIndex, or any RAG pipeline. pip install longtracer

Official repository of FEVER@ACL 2025 paper "When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification"

A retrieval-augmented generation-based framework for automatically constructing a hierarchy of aspects typically considered when addressing a nuanced claim and enriching them with corpus-specific perspectives.

Search infrastructure for AI agents: free by default, MCP-ready, LLM-context aware, and production-grade when needed.

Latent-Explorer is the Python implementation of the framework proposed in the paper "Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph".

An AI-powered system for automated academic peer review. Upload a PDF, and the assistant analyzes novelty, plagiarism, factual accuracy, claim mapping, and citation quality (via GROBID). Includes an optional Deep Search mode to fetch and index new papers for comparison

Intell Weave is a production-minded, scalable news platform that ingests the web, understands content (text + media), verifies claims, and serves hyper-personalized, explainable feeds — all powered by modern NLP, embeddings, and clean engineering.

Table-Text Alignment: Explaining Claim Verification

Tathya (तथ्य, "truth") is an Agentic fact-checking system that verifies claims using multiple sources including Google Search, DuckDuckGo, Wikidata, and news APIs. It provides structured analysis with confidence scores, detailed explanations, and transparent source attribution through a modern Streamlit interface and FastAPI backend.

Verify claims using AI agents that debate using scraped evidence and local language models.

Subjectivity-aware RAG pipeline for investment questions with web search, multi-strategy scraping, Worker + Checker LLMs, and deterministic claim verification.

POC: marketing claim + dark-pattern audit for commercial web pages. CLI + local web UI that fetches a page, extracts claims, classifies their verifiability, and flags dark patterns.

The Robustness of Multimodal LLMs in Reviewing Evidence from Tables and Charts

MCP server for Claude Desktop that applies Popperian falsifiability to verify claims from social media, news and blogs — with real academic sources, not opinions.

Codes for Paper "Verify-in-the-Graph: Entity Disambiguation Enhancement for Complex Claim Verification with Interactive Graph Representation"

RAG Worker service: executes retrieval, evidence validation, and LLM-based truth scoring pipelines.

MCP server for AgentOracle — claim verification for AI agents. Verify before you act. x402-native on Base, SKALE, Stellar.

Deterministic local proof harness for verifying AI agent recommendation claims against source-of-truth fixtures, with append-only outcome logs.

Open benchmark comparing AgentOracle's multi-source verification against GPT-4o on 200 FEVER claims. Adversarial layer catches 94% of refutations.