Claim Verification Python Packages

citevahti

Run unit tests on your manuscript. Check every manuscript claim against its cited evidence. Human-first, AI-second, Zotero-audited, local-first.

falsiflow

Stop unverifiable AI eval, product metric, and R&D claims from passing CI.

cross-validated-search

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

frame-check-mcp

Structural framing analysis as an MCP server with deterministic detection. The caller's agent runs the judge, so Frame Check bears zero LLM cost per query.

zero-api-key-web-search

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

longtracer

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

free-web-search-ultimate

Universal Search-First Knowledge Acquisition Plugin for LLMs (MCP + CLI-Anything)

arbiter-debate

Formally verified multi-agent debates

langchain-agentoracle

Trust layer for AI agents. Verify before you act. Per-claim verification via 4 independent sources. x402-native on Base, SKALE, Stellar.

latent-explorer

A Python library based on the technique of activation patching to represent the factual knowledge encoded in the latent space of large language models as dynamic knowledge graphs.