Skip to content

FairSense-AgentiX

An open-source platform from the Vector Institute for multi-modal bias detection, explainable fairness auditing, and retrieval-based mapping of deployment scenarios to the MIT AI Risk Repository and NIST AI RMF.

JOSS PyPI Zenodo Docs CI

Peer-reviewed open-source software

FairSense-AgentiX was published in the Journal of Open Source Software on 30 October 2026 (DOI: 10.21105/joss.11060). Software archive: Zenodo 10.5281/zenodo.23106857 (release v0.2.2). If you use this work in research, please cite the JOSS paper.


What is FairSense-AgentiX?

FairSense-AgentiX detects bias in text and images and assesses AI deployment scenarios against established risk frameworks. It uses a LangGraph orchestrator with a critique-and-refine loop—not a single-pass black-box classifier—so results include spans, explanations, scores, and step-by-step telemetry when you use the API or UI.

An orchestrator routes each request by declared modality (text, image, or scenario), runs the matching workflow, evaluates output quality with an LLM critic, and optionally refines before finalizing. Tools (OCR, vision models, embeddings, FAISS, LLMs) are injected via a registry so the same graphs run with real providers in production or lightweight fakes in CI.


Analysis modes

  • Text bias


    Structured instances (type, severity, span, explanation) and HTML highlights.

    User guide

  • Image bias


    OCR/captioning or a vision-language path, then the same bias pipeline as text.

    User guide

  • Risk assessment


    Semantic search over 1,538 MIT AI Risk Repository (V4, Dec 2025) risks plus NIST AI RMF–aligned actions.

    User guide


Key capabilities

Agentic orchestration

  • Modality-based routing into specialised LangGraph subgraphs
  • Post-hoc LLM evaluation (0–100) with configurable refinement
  • WebSocket telemetry for live agent timelines in the React UI

Production APIs

Configurable stack

  • LLM providers (OpenAI, Anthropic, OpenAI-compatible endpoints) or fake for tests
  • Swappable OCR/caption/embedder tools via environment variables

How it works

Every request follows the same orchestrator loop: route → execute → evaluate → deliver (with an optional refine pass when the critic score is low).

Input Route Execute Evaluate Results

Refine may send the request back to Route when quality is below threshold (capped).

  • 1 · Route


    Choose text, image, or risk workflow from the request and run preflight checks.

  • 2 · Execute


    Run the LangGraph subgraph: bias pipeline, OCR/VLM path, or FAISS over 1,538 MIT risks.

  • 3 · Evaluate


    LLM critic scores output (0–100). Fail → refine; pass → finalize.

  • 4 · Deliver


    Spans, explanations, highlights, risk matches, and agent telemetry.

Full orchestrator diagram


Quick start

=== "PyPI"

```bash
pip install fairsense-agentix
export FAIRSENSE_LLM_PROVIDER=openai
export FAIRSENSE_LLM_API_KEY=sk-...
```

=== "Source"

```bash
git clone https://github.com/VectorInstitute/fairsense-agentix.git
cd fairsense-agentix
uv sync && source .venv/bin/activate
```

Configure a real LLM provider first

The default FAIRSENSE_LLM_PROVIDER is fake (synthetic placeholders for tests). See Getting Started before running real analyses.

from fairsense_agentix import FairSense

engine = FairSense()
result = engine.analyze_text(
    "We're looking for a young, energetic developer to join our startup team."
)
print(result.summary)

Full getting started guide


Documentation map

Guide Description
Getting Started Install, .env, first analysis
User Guide Text, image, and risk workflows
Server Guide FastAPI + React UI
Architecture Graphs, tools, orchestrator
API Reference Python and REST
Developer Guide Contributing and extending
MIT risk index Bundled V4 corpus and RMF semantics
Changelog Release notes (e.g. v0.3.0)

Use cases

  • Content & marketing


    Moderation pipelines, ad copy, and inclusivity reviews before publish.

  • HR & policy


    Job posts, internal communications, and DEI alignment checks.

  • ML governance


    Pre-deployment risk mapping, audit trails, and fairness research with agent metadata.


Citation

If you use FairSense-AgentiX in academic work, please cite the JOSS article:

@article{Narayanan2026,
  doi = {10.21105/joss.11060},
  url = {https://doi.org/10.21105/joss.11060},
  year = {2026},
  publisher = {The Open Journal},
  volume = {11},
  number = {126},
  pages = {11060},
  author = {Narayanan, Aravind and Sekhon, Karanpal and Alinoori, Mahshid and Raza, Shaina},
  title = {FairSense-AgentiX: An Agentic Platform for Multi-Modal Fairness and AI Risk Analysis},
  journal = {Journal of Open Source Software}
}

License & support

MIT License · Issues · Contributing

Built with by the Vector Institute AI Engineering team.