interviewstreet/hiring-agent

Project overview

Automates resume evaluation by extracting structured data from PDFs, enriching it with GitHub activity, and producing explainable category scores with fairness constraints. It runs locally via a command-line interface and requires an external LLM backend such as Ollama or Google Gemini to operate.

Project type

AI Agent · RAG

Use cases

Documents & Office

Deployment

Refer to project documentation

License

MIT

Best for

• Developer and enterprise teams building automated office workflows for candidate evaluation who require explainable scoring rubrics.

Key capabilities

• Converts PDF pages to Markdown-like text using PyMuPDF and extracts sectioned JSON for structured processing.
• Fetches GitHub profile and repos, classifies projects, and prompts the language model to select the top 7 repositories.
• Runs a strict-scored evaluation with fairness constraints and produces category scores, evidence, bonus points, and deductions.
• Orchestrates end-to-end scoring from a PDF path and writes CSV output when development mode is enabled.

Limitations and risks

• The system requires Python 3.11 or newer.

Getting started

• Clone the repository, install dependencies using pip, install Ollama and pull a model or configure Gemini, set up the .env file, and run python score.py with the path to the target resume PDF.

Evidence and sources

• GitHub project description: AI agent to evaluate and score resumes.
• README: <p align="center"><strong>Resume-to-Score pipeline</strong> that extracts structured data from PDFs, enriches with GitHub signals, and outputs a fair, explainable evaluation.</p>…
• README: Hiring Agent parses a resume PDF to Markdown, extracts sectioned JSON using a local or hosted LLM, augments the data with GitHub profile and repository signals, then produces an o…
• README: - **Python 3.11+** The repository pins `.python-version` to 3.11.13. - **One LLM backend** (either of them) - **Ollama** for local models Install from the [official site](https://…
• README: 1. `pymupdf_rag.py` converts PDF pages to Markdown-like text. 2. `pdf.py` calls the LLM per section using Jinja templates under `prompts/templates`.

Reviewed at: 2026-07-16T23:15:59Z