ResumeForge: A Privacy-First AI Resume Analyzer Built with Local Open-Weight Models
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built Every time someone applies for a job today, they are handed the same advice: "Tailor your resume to the job description." But behind that simple advice is a frustrating dilemma. Existing commercial resume optimization tools charge $20 to $40 a month. Worse, they demand that you upload your entire…
ResumeForge is an AI-powered resume analysis and tailoring platform that operates entirely on your personal computer using open-weight models. It eliminates the need for cloud-based AI inference, subscriptions, and the sharing of any personal data. Users simply upload their existing resume (as either a .pdf or .docx file) and provide a target job description. The local AI engine then extracts the content, parses the role requirements, and feeds them to an on-device model through Docker Model Runner.
The tool provides a rigorous, calibrated analysis with a fit score ranging from 0 to 100. This score is accompanied by a 1-2 sentence justification explaining the reasoning behind the score. The analysis also includes a side-by-side comparison of the user's skills against the job description, highlighting any missing or excessive skills.
It offers targeted suggestions for each section of the resume (Experience, Summary, Projects, Skills) and highlights high-priority ATS keywords to help the resume pass through Applicant Tracking Systems.
Users can view their original resume PDF alongside the AI audit, with full authentication and persistent session history. The project is open-source and available for those who wish to clone the codebase. ResumeForge caters to privacy-conscious tech professionals, bootcamp graduates, career changers, and freelance recruiters who need a fast, efficient, and secure way to optimize their resumes for job applications without the risks associated with cloud-based services.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
