Parses PDF resumes to extract skills, predict candidate job roles, and generate recruitment analytics.
Extract applicant skills, structure candidate data into MySQL, and generate aggregate hiring metrics.
AI-Resume-Analyzer is a Python and Streamlit tool designed to parse resume PDFs, extract candidate skills, and score applicants against target roles. It helps HR teams and placement departments transform unstructured resumes into structured data for talent analytics.
The application parses incoming PDF resumes using NLP libraries like spaCy and PyResparser to pull basic contact info, skills, and key terms. It matches parsed profiles against predefined job sectors, suggests missing skills or training videos to applicants, and logs candidate metrics into a MySQL backend with CSV export features.
This tool suits academic placement cells and small internal recruitment teams looking for an open-source parsing prototype to aggregate applicant datasets. It does not suit enterprise HR environments requiring out-of-the-box ATS integrations, strict security compliance, or non-technical deployment.
Parses PDF resumes using natural language processing to extract applicant contact information, skills, and key terms.
Matches extracted resume keywords against domain criteria to predict job roles and estimate experience levels.
Displays aggregate pie charts for candidate experience, locations, and resume scores with CSV data export capabilities.
Generates tailored course and skill suggestions for applicants based on keyword gaps found in their resumes.
The codebase is free and open-source under the MIT license. The author mentions an optional third-party commercial platform (CVInsight) for users who want a managed product, but self-hosting this repository incurs only your own server and database costs.
880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
Out of the box, the script explicitly calls MySQL syntax and connections in App.py, requiring code refactoring to use PostgreSQL or SQLite.
The default NLP pipeline uses spaCy's English model (en_core_web_sm), meaning non-English resumes will not parse accurately.
No, this is a local project designed to run directly on your own infrastructure using Python and Streamlit.
See Zekai first in Google