| cff-version: 1.2.0 | |
| message: "If you use this software, please cite it as below." | |
| authors: | |
| - family-names: "Silva" | |
| given-names: "Anderson Henrique da" | |
| orcid: "https://orcid.org/0000-0000-0000-0000" | |
| email: "andersonhs27@gmail.com" | |
| affiliation: "Instituto Federal de Educação, Ciência e Tecnologia do Sul de Minas Gerais - Campus Muzambinho" | |
| title: "Cidadão.AI: Multi-Agent AI System for Brazilian Government Transparency Analysis" | |
| version: 1.0.0 | |
| doi: 10.5281/zenodo.0000000 | |
| date-released: 2025-01-20 | |
| url: "https://github.com/anderson-ufrj/cidadao.ai" | |
| repository-code: "https://github.com/anderson-ufrj/cidadao.ai" | |
| license: Apache-2.0 | |
| type: software | |
| keywords: | |
| - artificial-intelligence | |
| - transparency | |
| - government | |
| - multi-agent-system | |
| - brazil | |
| - public-data | |
| - corruption-detection | |
| - anomaly-detection | |
| - SDG16 | |
| - open-government | |
| - civic-tech | |
| - langchain | |
| - fastapi | |
| - machine-learning | |
| abstract: | | |
| Cidadão.AI is an innovative platform that uses specialized artificial intelligence | |
| to democratize access to Brazilian public data. The system employs a sophisticated | |
| multi-agent architecture to analyze government contracts, bidding processes, public | |
| expenses, and other government documents. It features eight specialized AI agents | |
| working collaboratively to detect anomalies, analyze patterns, and generate | |
| comprehensive reports, contributing directly to SDG 16: Peace, Justice and Strong | |
| Institutions. The platform provides both web interfaces (Gradio and Streamlit) and | |
| a REST API for programmatic access, making government transparency data accessible | |
| to citizens, journalists, researchers, and civil society organizations. | |
| references: | |
| - type: software | |
| authors: | |
| - name: "LangChain Contributors" | |
| title: "LangChain: Building applications with LLMs through composability" | |
| year: 2023 | |
| url: "https://github.com/langchain-ai/langchain" | |
| - type: software | |
| authors: | |
| - name: "FastAPI Contributors" | |
| title: "FastAPI: Modern, fast web framework for building APIs" | |
| year: 2023 | |
| url: "https://github.com/tiangolo/fastapi" | |
| - type: article | |
| authors: | |
| - family-names: "Vaswani" | |
| given-names: "Ashish" | |
| - family-names: "Shazeer" | |
| given-names: "Noam" | |
| - family-names: "Parmar" | |
| given-names: "Niki" | |
| title: "Attention is All You Need" | |
| journal: "Advances in Neural Information Processing Systems" | |
| volume: 30 | |
| year: 2017 | |
| - type: data | |
| authors: | |
| - name: "Controladoria-Geral da União" | |
| title: "Portal da Transparência do Governo Federal" | |
| year: 2025 | |
| url: "https://portaldatransparencia.gov.br" | |
| preferred-citation: | |
| type: software | |
| authors: | |
| - family-names: "Silva" | |
| given-names: "Anderson Henrique da" | |
| title: "Cidadão.AI: Multi-Agent AI System for Brazilian Government Transparency Analysis" | |
| year: 2025 | |
| doi: 10.5281/zenodo.0000000 | |
| url: "https://github.com/anderson-ufrj/cidadao.ai" |