BiasScope
cognis-digital/biascope
Detecção embarcada de vieses demográficos, ocupacionais e geográficos em LLMs
Ver no GitHubSuite de detecção de vieses embarcada para modelos de IA, identificando preconceitos demográficos, ocupacionais e geográficos. Opera como MCP server integrado ao Claude Desktop e Cursor, permitindo auditorias autônomas de LLMs e agentes sem infraestrutura pesada.
Instalação
npx convez-ai cognis-digital/biascope1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Auditar sistemas de aprovação de crédito e empréstimos para vieses discriminatórios
- Testar chatbots e agentes de IA antes de deploy em produção
- Integrar verificações de viés em pipelines de CI/CD como checks obrigatórios
- Gerar relatórios SARIF para análise em IDEs e GitHub Security
Veredito

Ferramenta especializada e bem-estruturada para governança de IA, resolvendo um problema concreto (detecção de vieses) com outputs versáteis (JSON, SARIF, HTML). Recomendada para times de segurança que precisam auditar modelos e agentes antes de produção.
README
A tradução para o português deste README ainda está na fila.
BIASCOPE — Embedded bias probe suite — demographic / occupational / geographic
Part of the Cognis Neural Suite by Cognis Digital Cognis Open Collaboration License (COCL) v1.0 · domain:
ai-security
Embedded bias probe suite — demographic / occupational / geographic.
AI Security & Governance — securing LLMs, agents, and the MCP supply chain.
Why
Security and intelligence teams need embedded bias probe suite — demographic / occupational / geographic without standing up heavyweight infrastructure. biascope is single-purpose, scriptable, CI-friendly, and self-hostable: point it at a target, get prioritized findings in the format your workflow already speaks (table, JSON, SARIF, HTML), and wire it into agents over MCP when you want it autonomous.
Install
pip install cognis-biascope
# or, from this repo:
pip install -e ".[dev]"
Quick start
biascope --version
biascope scan demos/ # run against the bundled demo
biascope scan demos/ --format sarif --out r.sarif --fail-on high
biascope scan demos/ --format html --out report.html
biascope mcp # expose as an MCP server (Cognis.Studio / Claude Desktop / Cursor)
Built-in demo scenarios
Each scenario folder includes a SCENARIO.md describing the situation and the findings to expect.
Output formats
- Table (default) — human-readable terminal summary
- JSON — machine-readable findings for pipelines
- SARIF — drops into GitHub code-scanning / IDE problem panes
- HTML — shareable report with severity rollups
Credits / Built on
Cognis composes and credits the best of open source. This tool builds on / interoperates with:
stanford-crfm/helm— probe datanyu-mll/BBQ— bias benchmark
Missing a credit? Open a PR — see CONTRIBUTING.md.
How it fits the Cognis Neural Suite
biascope is one of 52 tools in the Cognis Neural Suite. Every tool ships an MCP server, so Cognis.Studio agents can call them as scoped capabilities.
Sibling tools in ai-security: aegis, promptmirror, ledgermind, adversa, guardpost, hallumark, aicard, mcpharden, agentlog, ragshield
Architecture & roadmap
- Design notes:
docs/ARCHITECTURE.md - Planned work:
ROADMAP.md
Contributing
PRs, new detections, and demo scenarios are welcome under the collaboration-pull model. See CONTRIBUTING.md and SECURITY.md.
License
Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.
Responsible use
This is dual-use security software. Use it only against systems, data, and identities you own or are explicitly authorized in writing to test, and in compliance with applicable law.
About
Cognis Digital — Wyoming, USA · Making Tomorrow Better Today: Advanced Cybersecurity, AI Innovation, and Blockchain Expertise.