interviewstreet/hiring-agent
AI agent pipeline for evaluating and scoring resumes by parsing PDFs with LLMs, fetching GitHub profile data, and producing objective candidate evaluations.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
The system converts resume PDFs to Markdown, then uses local or hosted LLMs (Ollama or Google Gemini) to extract structured JSON data per section via Jinja templates. It augments the resume data with GitHub profile and repository signals, classifies projects, and selects top contributions. The final evaluator produces category scores, evidence, bonus points, and deductions with fairness constraints, orchestrated end-to-end by a CLI.