Home/Evaluation & Observability/anti-lie

anti-lie

lc198707/anti-lie

An LLM Claim Auditing Layer with truth gradients for verifying factual claims

GitHub Website

GraphCanon updated Sep 9, 2026 · GitHub synced Sep 9, 2026

27views this month

89 stars6 forksLast push May 10, 2026 Python Other

Decision brief

Anti-Lie offers an LLM claim auditing layer using T1-T7 truth gradients to achieve high business effectiveness on fact-checking benchmarks.

Good fit when

When you require high accuracy in verifying factual claims made by LLMs, achieving a reported 98.1% effectiveness on benchmark testing with LiarBench v0.2
If your environment supports Python and requires seamless integration of an audit tool into agent runtimes or open-source toolchains

Avoid when

When the target platform is not Linux or macOS, as current service definitions are specific to these operating systems (systemd for Linux, launchd for macOS)
If your project does not require an outbound hook bundle including both a Python verifier and a Node.js shadow worker

Pricing:: freemium - The software is free (open source). However, additional compliance documents may incur costs or delays.

Observed Jul 16, 2026 · Source: enrich:decision_facts

anti-lie alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Slowing (121d since push); As of Sep 9, 2026
Provenance: Not a fork · Personal account; As of Sep 9, 2026
Security (OSV): No lockfile; As of Jul 15, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install anti-lie

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

awesome-LLM-resources

Summary of the world's best LLM resources.

9.0k★

PurpleLlama

Set of tools to assess and improve LLM security

4.4k★

LLMDebugger

A Large Language Model Debugger verifying runtime execution step by step

584★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Anti-Lie provides a verification service that can audit and grade the factual accuracy of LLM outputs using T1-T7 truth gradients, targeting 98.1% business effectiveness on LiarBench v0.2.

Capability facts

Languages: python
Source: github.language · Sep 9, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Node.js runtimeNode.js

Source: README excerpt (regex_v1, Sep 9, 2026)

as an OpenClaw outbound hook bundle that includes a Python verifier service, a Node.js shadow worker, and platform-specific service definitions for Linux (systemd) an

Source link

Python runtimePython

Source: README excerpt (regex_v1, Sep 9, 2026)

Anti-Lie is distributed as an OpenClaw outbound hook bundle that includes a Python verifier service, a Node.js shadow worker, and platform-specific service definit

Source link

README

Quick Start Anti Lie is distributed as an OpenClaw outbound hook bundle that includes a Python verifier service, a Node.js shadow worker, and platform specific service definitions for Linux (systemd) and macOS (launchd). ```bash git clone https://github.com/lc198707/anti lie.git...

For agents

This page has a .md twin and JSON over the API.

/tools/lc198707-anti-lie.md GET /api/graphcanon/tools/lc198707-anti-lie GET /api/graphcanon/graph?tool=lc198707-anti-lie