NarrativeDiff
cognis-digital/narrativediff
Análise de viés narrativo em meios de notícia com MCP nativo
Ver no GitHubMCP server que analisa viés noticioso e diferenças de enquadramento em 50+ veículos de comunicação por evento. Executa em qualquer infraestrutura, integra-se com agentes de IA e produz resultados em múltiplos formatos (tabela, JSON, SARIF) prontos para CI/CD.
Instalação
npx convez-ai cognis-digital/narrativediff1 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
- Verificar variações de cobertura jornalística entre diferentes outlets
- Integrar análise de viés em pipelines CI/CD de informação
- Investigação de narrativas e framing político em eventos críticos
Veredito

Ferramenta especializada em análise de integridade informacional com suporte nativo a MCP. Útil para jornalistas, pesquisadores e organizações que precisam auditar viés narrativo em larga escala, mas requer domínio técnico para maximizar seu potencial.
README
A tradução para o português deste README ainda está na fila.
NARRATIVEDIFF
News bias & framing diff across 50+ outlets per event
Information Integrity — provenance, synthetic-media, and narrative analysis.
pip install cognis-narrativediff
narrativediff scan . # → prioritized findings in seconds
Contents
- Why narrativediff? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing
Why narrativediff?
News bias & framing diff across 50+ outlets per event — without standing up heavyweight infrastructure.
narrativediff is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.
Features
- ✅ Analyze Event
- ✅ Load Corpus
- ✅ Result To Dict
- ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
- ✅ Ports in Python, JavaScript, Go, and Rust (
ports/)
Quick start
pip install cognis-narrativediff
narrativediff --version
narrativediff scan . # scan current project
narrativediff scan . --format json # machine-readable
narrativediff scan . --fail-on high # CI gate (non-zero exit)
Example
$ narrativediff scan .
[HIGH ] NAR-001 example finding (./src/app.py)
[MEDIUM ] NAR-002 another signal (./config.yaml)
2 findings · risk score 5 · 38ms
Architecture
flowchart LR
A[Input: file / dir / API] --> B[Collectors]
B --> C[Rules / Analyzers]
C --> D[Scorer]
D --> E{Reporters}
E --> F[Table]
E --> G[JSON / SARIF]
E --> H[MCP tool -. drives .-> AI agents]
Use it from any AI stack
narrativediff is interoperable with every popular way of using AI:
- MCP server —
narrativediff mcp(Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet) - OpenAI-compatible / JSON — pipe
narrativediff scan . --format jsoninto any agent or LLM - LangChain · CrewAI · AutoGen · LlamaIndex — wrap the CLI/JSON as a tool in one line
- CI / scripts — exit codes + SARIF for non-AI pipelines
How it compares
| Cognis narrativediff | Media-Bias-Group | |
|---|---|---|
| Self-hostable, no account | ✅ | varies |
| Single command, zero config | ✅ | ⚠️ |
| JSON + SARIF for CI | ✅ | varies |
| MCP-native (AI agents) | ✅ | ❌ |
| Polyglot ports (JS/Go/Rust) | ✅ | ❌ |
| Open license | ✅ COCL | varies |
Built in the spirit of Media-Bias-Group/MBIB, re-framed the Cognis way. Missing a credit? Open a PR.
Integrations
Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (narrativediff mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.
Install — every way, every platform
pip install "git+https://github.com/cognis-digital/narrativediff.git" # pip (works today)
pipx install "git+https://github.com/cognis-digital/narrativediff.git" # isolated CLI
uv tool install "git+https://github.com/cognis-digital/narrativediff.git" # uv
pip install cognis-narrativediff # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/narrativediff:latest --help # Docker
brew install cognis-digital/tap/narrativediff # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/narrativediff/main/install.sh | sh
| Linux | macOS | Windows | Docker | Cloud |
|---|---|---|---|---|
scripts/setup-linux.sh | scripts/setup-macos.sh | scripts/setup-windows.ps1 | docker run ghcr.io/cognis-digital/narrativediff | DEPLOY.md (AWS/Azure/GCP/k8s) |
Related Cognis tools
claimtrace— Misinformation provenance tracer — earliest-known appearance graphdeepcheck— Lightweight synthetic-media detector with C2PA validationelectionlens— Influence-operations pattern monitor for election periods
Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 hermes
Contributing
PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.
⭐ If
narrativediffsaved you time, star it — it genuinely helps others find it.
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.