Skip to main content

Credit Card Recommender

Compara tarjetas de crédito usando sus páginas oficiales y recomienda una opción.

Requisitos

  • Python 3.13+
  • uv
  • Una clave de API de OpenAI con saldo disponible

Instalación

uv sync
cp .env.example .env

Agrega tu clave en .env:

OPENAI_API_KEY=openai_api_key
TYPESAFE_API_KEY=typesafe_api_key
OPENAI_DEFAULT_MODEL=gpt-5.6-luna
OPENAI_AGENTS_DONT_LOG_MODEL_DATA=1
OPENAI_AGENTS_DONT_LOG_TOOL_DATA=1

Ejecutar

Configura las URLs que quieras comparar en harness/cards_analyzer.py y ejecuta:

uv run python harness/cards_analyzer.py

El programa extrae los datos de cada tarjeta, las compara y recomienda una. Los logs muestran el uso de tokens por llamada.

Uso como librería

import asyncio
from credit_card_agent_recommender import CreditCardAnalyzer, CreditCardRecommender


async def main():
    analyzer = CreditCardAnalyzer()
    analysis = await analyzer.analyze_cards([
        "https://www.viabcp.com/tarjetas/american-express-platinum",
        "https://www.bbva.pe/personas/productos/tarjetas/credito/tarjeta-platinum.html",
    ])

    recommender = CreditCardRecommender()
    recommendation = await recommender.recommend(analysis)
    print(recommendation)


asyncio.run(main())

Consideraciones

  • Cada tarjeta requiere una llamada de extracción al modelo; luego hay una llamada de análisis y otra de recomendación. El consumo depende del contenido enviado y del modelo configurado.
  • El acceso depende del sitio. El programa no elude bloqueos ni verificaciones anti-bot.
  • No compartas ni subas .env al repositorio.

Metadata

Release files for credit-card-agent-recommender 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for credit-card-agent-recommender 0.1.1
File Size Uploaded
credit_card_agent_recommender-0.1.1.tar.gz 9.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for credit-card-agent-recommender 0.1.1
File Interpreter ABI Platform
credit_card_agent_recommender-0.1.1-py3-none-any.whl Python 3 none any Details

Total release size: 26.4 kB

Release files / credit_card_agent_recommender-0.1.1.tar.gz

Download URL credit_card_agent_recommender-0.1.1.tar.gz
Size 9.4 kB
Tags Source
SHA-256 checksum
How to use checksums
7785e50b3d5299285e359a5dea1b475af1162d59982538ab2ebaeb379bc41b38
BLAKE2b-256 checksum
How to use checksums
73d269fb79043d9ab1757f4ccbb8551a947c972b1ca4dd5b3cef59764c83c72d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 18, 2026.

Transparency log

Release files / credit_card_agent_recommender-0.1.1-py3-none-any.whl

Download URL credit_card_agent_recommender-0.1.1-py3-none-any.whl
Size 17.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
5f2e6af6cf1993cac278d91038c3165f97185ca64c525be9a4c0a2c3b44d8bc3
BLAKE2b-256 checksum
How to use checksums
d3ee27cf79a4022b3b33148dc1765982e68a90f5f774b75c035d20058d85a91a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 18, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page