Claim Verification Python Packages

testguard-cli

Claim-driven mutation testing: inject faults and report what your tests miss. Vitest, Jest, Playwright, pytest & unittest. Part of the Guard family with DocGuard and WebSec Validator.

agenda-intelligence-md

Deterministic evidence-packet checks for AI-generated claims: references, quotes, numbers, and support gaps. CLI, Python, MCP, and review adapters.

citevahti

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

claimbound-evidence

Evidence cards for narrow public AI, ML and data claims: frozen protocol, hashed sources, honest result status.

whypass

A claim-discipline linter for text — catch assertions that outrun their evidence, and claims that contradict your record. Not a lie detector.

falsiflow

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

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.

claimstamp

Ground an agent's claims in commands it actually ran, not commands it says it ran.

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

arbiter-debate

Open-source framework for formally verifying academic paper claims using multi-agent LLM debate + Z3/Knuckledragger proof certificates. Supports OpenAI, Anthropic, Google, Grok.

latent-explorer

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".