Top AI Product

Resume screening is the part of hiring everyone hates and nobody does well. hiring-agent, an open-source tool from HackerRank (interviewstreet) trending on GitHub, automates it — and notably, it doesn’t just read the resume, it goes and checks your code.

## How it works

The agent converts a resume PDF to markdown with PyMuPDF, then uses an LLM — run locally via Ollama or hosted Gemini — to extract a structured JSON profile. The interesting step is GitHub enrichment: it pulls the candidate’s username, fetches their repos, and asks the model to pick seven real projects that clear a minimum author-commit threshold. Then it scores across categories like open source, personal projects, production work, and technical skills, with bonus points, deductions, and written evidence for each call.

## Why it matters

Most AI resume screeners just pattern-match keywords and inherit every bias in the training data. Grounding the score in actual commit history is a meaningfully different approach — it rewards what someone built, not how they phrased it. Running fully local is the other tell: candidate data is sensitive, and a screener you can run on Ollama never sends resumes to a third party.