{"data":{"slug":"lc198707-anti-lie","name":"anti-lie","tagline":"An LLM Claim Auditing Layer with truth gradients for verifying factual claims","github_url":"https://github.com/lc198707/anti-lie","owner":"lc198707","repo":"anti-lie","owner_avatar_url":"https://avatars.githubusercontent.com/u/282125071?v=4","primary_language":"Python","stars":89,"forks":6,"topics":["agent-skills","ai-safety","anti-lie","audit","factuality","guardrails","hallucination","liarbench","llm","llm-evaluation","openclaw","truthfulness"],"archived":false,"github_pushed_at":"2026-05-10T14:23:28+00:00","maintenance_label":"Slowing","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/lc198707-anti-lie","markdown_url":"https://www.graphcanon.com/tools/lc198707-anti-lie.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lc198707-anti-lie","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lc198707-anti-lie","description":"Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effectiveness on LiarBench v0.2.","homepage_url":"https://github.com/lc198707/anti-lie","license":"Other","open_issues":0,"watchers":4,"ai_summary":"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.","readme_excerpt":"## Quick Start\n\nAnti-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).\n\n```bash\ngit clone https://github.com/lc198707/anti-lie.git\ncd anti-lie/skill\nbash install.sh        # Linux\n\n---\n\n## License\n\nMIT License — see LICENSE.\n\nMIT is the project license. Anti-Lie is meant to be easy to inspect, fork, embed, and improve in agent runtimes, internal audit systems, and open-source toolchains. If your organization needs additional compliance documents, open an issue rather than hiding legal assumptions in README prose.","github_created_at":"2026-05-10T13:51:44+00:00","created_at":"2026-07-15T10:39:22.939181+00:00","updated_at":"2026-09-20T04:24:51.403466+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"agent-skills","name":"agent-skills"},{"slug":"ai-safety","name":"ai-safety"},{"slug":"anti-lie","name":"anti-lie"},{"slug":"audit","name":"audit"},{"slug":"factuality","name":"factuality"},{"slug":"guardrails","name":"guardrails"},{"slug":"hallucination","name":"hallucination"},{"slug":"liarbench","name":"liarbench"}],"trust":{"provenance":{"is_fork":false,"github_id":1234674650,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-09T06:00:12.774Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":121,"last_release_at":"2026-05-10T14:23:28Z","stars_delta_30d":0,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:39:24.308Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-09T06:00:13.422Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-09T06:00:13.422Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-09T06:00:13.422Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The software is free (open source). However, additional compliance documents may incur costs or delays."},"requirements":{"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"when_to_use":["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"],"when_not_to_use":["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"],"source":"enrich:decision_facts","observed_at":"2026-07-16T19:05:54.036Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - The software is free (open source). However, additional compliance documents may incur costs or delays."},{"label":"Adopt for","value":"Anti-Lie offers an LLM claim auditing layer using T1-T7 truth gradients to achieve high business effectiveness on fact-checking benchmarks."},{"label":"License detail","value":"MIT License, allows easy integration, inspection, forks, embeds, and improvements of the tool in various agent runtimes and audit systems."}]}}