Ai Verification Python Packages

mettle-verifier

Inverse Turing test for AI agents. Procedurally generated challenges that prove substrate, autonomy, and intent — things a human can't fake. Self-hosted, open source, Apache-2.0 licensed.

andon-verify

Deterministic verification for AI-generated analysis. Reconciliation, consistency and Excel-integrity checks that stop the line when the numbers don't add up.

false-feet-algorithm

False Feet Algorithm: Multi-branch hypothesis evaluation with inverse resource allocation. Solves complex problems through adaptive reasoning—includes mystery solver demo + generic framework for any domain.

runopsy-replay

Find where an AI agent run started going wrong - not just where it stopped. Local-first causal failure analysis with counterfactual replay.

runopsy-cli

Find where an AI agent run started going wrong - not just where it stopped. Local-first causal failure analysis with counterfactual replay.

runopsy

Find where an AI agent run started going wrong - not just where it stopped. Local-first causal failure analysis with counterfactual replay.

runopsy-core

Find where an AI agent run started going wrong - not just where it stopped. Local-first causal failure analysis with counterfactual replay.

runopsy-collector

Find where an AI agent run started going wrong - not just where it stopped. Local-first causal failure analysis with counterfactual replay.

runopsy-inspect

Find where an AI agent run started going wrong - not just where it stopped. Local-first causal failure analysis with counterfactual replay.

qwed-tax

The Verification Gate for AI-Generated Tax Decisions. Deterministic tax verification layer powered by Z3 and Decimal math — sits between AI agents and execution systems. Not a calculator, not a filing platform.

runopsy-server

Find where an AI agent run started going wrong - not just where it stopped. Local-first causal failure analysis with counterfactual replay.

runopsy-semantic

Find where an AI agent run started going wrong - not just where it stopped. Local-first causal failure analysis with counterfactual replay.

runopsy-adapter

Find where an AI agent run started going wrong - not just where it stopped. Local-first causal failure analysis with counterfactual replay.

runopsy-bench

Find where an AI agent run started going wrong - not just where it stopped. Local-first causal failure analysis with counterfactual replay.

qwed-ucp

Verification for Universal Commerce Protocol (UCP) transactions — Deterministic verification layer for UCP checkouts: catches math, state, and schema errors before payment.

nowreck

A CLI tool that verifies AI coding assistant claims against actual structural changes — catching hallucinated functions, fake calls, and missed modifications before they ship.

glassbox-framework

Glass Box Framework — runtime constitutional verification for AI answers. Trust Cards with claim-level reasoning chains, formal ECS scoring, the 7-angle Glassbox Court red team, and deterministic audit logs. MCP-native.

rooben

Spec-driven multi-agent orchestration with verification and budget enforcement. Your taste is the product.

liminate-invariant

Verify what AI agents claim, not just what they're allowed to do. Semantic verification for the Liminate ecosystem.

opengate-grounding

Don't trust AI. Verify it. Open-source verification for evidence-grounded AI — deterministic grounding checks against source evidence, no LLM judge. CLI, GitHub Action, Python, MCP server, Docker.