Stock Purchase Analyzer

C 65 completed
Web App
unknown / python · small
57
Files
3,823
LOC
3
Frameworks
3
Languages

Pipeline State

completed
Run ID
#366862
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
52.22
Framework unique
Isolation
Last stage change
2026-05-10 03:35:31
Deduplication group #49553
Member of a group with 12 similar repo(s) — canonical #28719 view group →
Top concepts (2)
Project DescriptionWeb Backend
Want this analysis on your repo? https://repobility.com/scan/

AI Prompt

Create a web-based stock purchase analyzer using Python. I need a platform that analyzes stocks by combining social media sentiment, fundamental data, and historical patterns. The core feature should be a multi-agent debate system involving five specialist AI agents and a moderator to generate investment recommendations. The system should be runnable via a Streamlit dashboard and also have a CLI option. It needs to support importing purchase history via CSV and use libraries like yfinance and pandas-ta for data sources.
python streamlit fastapi ai stock-analysis finance multi-agent data-science investing
Generated by gemma4:latest

Catalog Information

A web-based platform that analyzes stocks by combining social media sentiment, fundamental data, and historical patterns to aid investment decisions.

Description

The system aggregates real‑time social media chatter, extracts key sentiment indicators, and merges them with fundamental metrics and historical price data. A set of lightweight AI agents process the combined data to generate actionable insights and recommendation scores for individual stocks. Users interact through a responsive web interface built with FastAPI and Streamlit, where they can query specific tickers, view visual dashboards, and download analytical reports. The platform targets retail and professional investors seeking a data‑driven approach to portfolio selection. It addresses the challenge of filtering noise from social signals and aligning them with quantitative fundamentals to reduce guesswork in trading.

الوصف

يستخلص النظام بيانات من وسائل التواصل الاجتماعي في الوقت الفعلي، ويحلل المشاعر المرتبطة بالأسهم، ثم يدمج هذه النتائج مع المقاييس الأساسية للقطاع والبيانات التاريخية للأسعار. يعمل مجموعة من الوكلاء الذكاء الاصطناعي الخفيفة على معالجة البيانات المجمعة لإنتاج توصيات قابلة للتنفيذ مع درجات اعتماد لكل سهم. يتفاعل المستخدمون مع واجهة ويب ديناميكية مبنية على FastAPI وStreamlit، حيث يمكنهم استعلام رموز الأسهم، عرض لوحات معلومات بصرية، وتحميل تقارير تحليلية. يستهدف المنصة المستثمرين الأفراد والمحترفين الذين يفضلون نهجاً مبنياً على البيانات لاتخاذ قرارات محفظة. يحل المشكلة التي تواجهها الأسواق في فحص الضوضاء من إشارات وسائل التواصل وتوافقها مع الأسس الكمية لتقليل التخمين في التداول.

Novelty

7/10

Tags

stock-analysis sentiment-analysis financial-forecasting data-visualization investment-decision-support

Technologies

beautifulsoup fastapi numpy pandas pydantic sqlalchemy streamlit uvicorn

Claude Models

claude-opus-4.6

Quality Score

C
65.3/100
Structure
72
Code Quality
82
Documentation
47
Testing
40
Practices
67
Security
74
Dependencies
60

Strengths

  • Code linting configured (ruff (possible))
  • Consistent naming conventions (snake_case)

Weaknesses

  • No LICENSE file \u2014 legal ambiguity for contributors
  • No CI/CD configuration \u2014 manual testing and deployment
  • Potential hardcoded secrets in 1 files
  • 112 duplicate lines detected \u2014 consider DRY refactoring

Recommendations

  • Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
  • Add a LICENSE file (MIT recommended for open source)
  • Move hardcoded secrets to environment variables or a secrets manager

Security & Health

7.6h
Tech Debt (D)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (5)
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/
Unknown
License
3.1%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
84.9%
markdown
13.6%
toml
1.5%

Frameworks

FastAPI pytest SQLAlchemy

Concepts (2)

Open data · scored by Repobility · https://repobility.com
CategoryNameDescriptionConfidence
All rows above produced by Repobility · https://repobility.com
auto_descriptionProject DescriptionAI-powered multi-agent stock analysis system. Uses specialist AI agents that debate each other to produce investment recommendations.80%
auto_categoryWeb Backendweb-backend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/91051.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV