# Libr-AI/OpenFactVerification

Loki: Open-source solution designed to automate the process of verifying factuality

Repository: https://github.com/Libr-AI/OpenFactVerification
Canonical: https://ross.abutalabs.com/products/openfactverification
Homepage: https://loki.librai.tech/
Language: Python
License: MIT
License Family: permissive
Topics: ai, factuality, hallucination
Last push: 2024-10-03T10:55:29+00:00

## Health v2 (maintenance only)
Score: 15/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 63
- inputs: {"age_days": 891, "days_push": 699, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1153, forks 64 (observed 2026-08-28T04:03:47.449787+00:00)

## What it is
Loki is an open-source Python tool that automates fact verification by decomposing texts into claims, retrieving evidence via search, and using LLMs to assess factuality. It supports text, speech, image, and video inputs and can be used as a library, CLI, or web app.

## Use cases
- verify factual claims in a text automatically
- detect hallucinations in LLM outputs
- fact-check articles as a journalist
- check factuality of speech or video content
- decompose long text into verifiable claims
- retrieve evidence from the web for claims

## When to choose
- you need automated fact-checking with an evidence retrieval pipeline
- you want a Python library or API to verify claims programmatically
- you need multimodal fact verification including speech, image, and video

## When to avoid
- you need a human-curated fact-checking database rather than automated verification
- you cannot provide LLM and search API keys
- you need fully offline fact-checking without web evidence retrieval

## Facets
- artifact type: library
- maturity: active
- function: nlp, machine-learning, llm-inference, web-scraping, search-engine, rag
- domain: artificial-intelligence, large-language-models
- platform: python, cli
- tags: fact-checking, factuality, hallucination-detection, claim-verification, misinformation, multimodal, evidence-retrieval, natural-language-processing, search, web-server

## Member repositories
- Libr-AI/OpenFactVerification (main) score 15

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:47.449787+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:33:25.502407+00:00, confidence not recorded.
  - readme: https://github.com/Libr-AI/OpenFactVerification (fetched 2026-08-28T04:03:47.449787+00:00, sha 03b1131e8928)
- Data as of 2026-08-30T08:39:29.467469+00:00.