AI analysis grounded in the code graph — computed facts, not vibes · 2026-07-05T09:38:00Z
Hiring Agent is a resume-to-score pipeline that parses a PDF résumé into Markdown-like text (pymupdf_rag.py), extracts sectioned JSON via an LLM (pdf.py), enriches the data with GitHub profile and repository signals (github.py), and produces a category-scored, evidence-backed evaluation (evaluator.py, score.py). It targets recruiters and engineering teams who want a reproducible, explainable candidate assessment, and it can run fully locally via Ollama or against Google Gemini. The tool is Python 3.11+ and MIT-licensed.
The star growth (1,647 this week) cannot be explained by the facts fetched here: there are no release notes and no commit titles for the last 30 days available for review. What evidence exists is the README's positioning around a topical use case — automated, "fair and explainable" candidate scoring with a local-first LLM option — and the fact that it originates from InterviewStreet (HackerRank's org), which likely lends credibility and distribution. Absent commit or release data, attributing the spike to a specific technical event would be speculation.
What changed recently, how it's actually built (from the code graph), and whether you should care. Free account — no card, no spam.