# okfn-brasil/serenata-de-amor

🕵 Artificial Intelligence for social control of public administration | **This repository does not receive frequent updates. Check out the README**

Repository: https://github.com/okfn-brasil/serenata-de-amor
Canonical: https://ross.abutalabs.com/products/serenata-de-amor
Homepage: https://serenata.ai/en
Language: Python
License: MIT
License Family: permissive
Topics: machine-learning, data-science, artificial-intelligence, politics, civic-tech, open-data
Last push: 2024-01-31T20:29:15+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3719, "days_push": 945, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4603, forks 654 (observed 2026-08-28T04:08:54.885567+00:00)

## What it is
Operação Serenata de Amor is an open-source data science project that uses machine learning to audit Brazilian congresspeople's public expense reimbursements and flag suspicious spending. It powers Rosie, an AI agent that analyzes expenses and posts findings on social media, and Jarbas, a web interface for browsing the flagged data.

## Use cases
- audit brazilian congresspeople expense reimbursements
- detect suspicious public spending with machine learning
- analyze CEAP parliamentary expense datasets
- browse and validate flagged expense suspicions
- build civic tech tools on open government data
- monitor public administration spending anomalies

## When to choose
- you want to analyze or audit Brazilian public expense data (Chamber of Deputies, Federal Senate)
- you need an example of applied machine learning for government accountability
- you want to contribute to or extend a civic tech open-data project

## When to avoid
- you need actively maintained software - the repo no longer receives frequent updates
- you need auditing of non-Brazilian government data without significant adaptation
- you need a production-ready turnkey fraud detection system rather than a research/civic project

## Facets
- artifact type: application
- maturity: maintenance
- function: machine-learning, data-science, nlp, web-scraping, analytics, data-visualization
- domain: data-science, artificial-intelligence, analytics, e-government
- platform: python
- tags: civic-tech, open-data, public-spending-audit, brazil, government-transparency, anomaly-detection, congressional-expenses, transparency, linux, docker, web

## Member repositories
- okfn-brasil/serenata-de-amor (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:54.885567+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:19:46.215283+00:00, confidence not recorded.
  - readme: https://github.com/okfn-brasil/serenata-de-amor (fetched 2026-08-28T04:08:54.885567+00:00, sha c7beccfe1a4e)
  - homepage: https://serenata.ai/en (fetched 2026-08-29T09:05:06.169555+00:00, sha a7207ba571c6)
  - site_page: https://serenata.ai/en/about (fetched 2026-08-29T09:05:06.172562+00:00, sha 6f44ba85137d)
  - site_page: https://serenata.ai/en/faq (fetched 2026-08-29T09:05:06.175990+00:00, sha 44d1da5adb11)
- Data as of 2026-08-30T08:39:29.467469+00:00.