Skip to content
Back to the index

onus

PyPIInfrastructure

PulseGate's liveness check found it on 5 Oct 2026; it is registered on PyPI and has been in the index since 5 Oct 2026. How this is checked

Onus is an MIT-licensed Python package and command-line claim checker. It extracts verifiable claims from decks or documents, compares them with evidence, and reports findings using Ruff-style rule codes for developers and research teams.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

6 features

Purpose: Checking factual claims in presentations and documents against supporting evidence.

Inferred · not functionally tested

Audience: developers and teams validating AI-generated or research-heavy documents

Inferred · not functionally tested

Functions: data_extraction

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org. These links do not verify the individual claims.

In the Other LLM eval space, onus takes a focused approach. Inferred · not functionally tested: It focuses on checking factual claims in presentations and documents against supporting evidence. Inferred · not functionally tested: It is built as an open-source project for developers and teams validating AI-generated or research-heavy documents. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It runs on the command line, and it can be self-hosted.

onus first shipped in 2026. Inferred · not functionally tested: Among its 6 catalogued features are claim extraction, evidence checking, and document analysis.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Claim extraction
  • Evidence checking
  • Document analysis
  • Deck analysis
  • Rule codes
  • Hallucination detection

Topics: Inferred · not functionally tested

Tags
claim-checkingfact-verificationdocument-groundingllm-linter
AI capabilities
TextStructured
Inference: Cloud API

JSON profile · Text profile · Access guide

Built with & integrations

Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen SourceFree tier

Indexing history

1

What PulseGate has recorded for this listing

  1. Indexed5 Oct · 18:54 UTC
    onus seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about onus

What is onus?
Inferred · not functionally tested: Onus focuses on checking factual claims in presentations and documents against supporting evidence. It is catalogued under Other LLM eval on PulseGate.
Who is onus for?
Inferred · not functionally tested: onus is an open-source project built for developers and teams validating AI-generated or research-heavy documents.
Is onus free?
Basis unknown · not verified: Yes — onus is open source under the MIT license and free to use.
What platforms does onus run on?
Basis unknown · not verified: onus runs on the command line. It can also be self-hosted.
Is onus still active?
PulseGate's liveness check found it on 5 Oct 2026.
What are alternatives to onus?
Similar projects tracked by PulseGate include Digraph, MonitorMyGEO, and BrandReply.DigraphMonitorMyGEOBrandReply
How long has onus been around?
onus first shipped in 2026.
Is onus open source?
Basis unknown · not verified: Yes — onus is open source under the MIT license.

Also in Other LLM eval

Same category — not a similarity match