Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
AI agent to evaluate and score resumes.
| Date | Stars |
|---|---|
| 2026-07-31 | 6648 |
| 2026-08-01 | 6674 |
| 2026-08-02 | 6674 |
| 2026-08-11 | 6845 |
| 2026-08-18 | 6917 |
| 2026-08-19 | 6941 |
| 2026-08-20 | 6953 |
| 2026-08-21 | 6960 |
| 2026-08-22 | 6967 |
| 2026-08-23 | 6978 |
| 2026-08-24 | 6988 |
| 2026-08-25 | 6994 |
| 2026-08-26 | 7001 |
| 2026-08-27 | 7011 |
| 2026-08-28 | 7018 |
| 2026-08-29 | 7029 |
| 2026-08-30 | 7033 |
| 2026-08-31 | 7047 |
| 2026-09-01 | 7068 |
| 2026-09-02 | 7078 |
| 2026-09-03 | 7079 |
| 2026-09-04 | 7084 |
| 2026-09-05 | 7093 |
| 2026-09-06 | 7097 |
| 2026-09-07 | 7110 |
| 2026-09-08 | 7138 |
| 2026-09-09 | 7144 |
| 2026-09-10 | 7152 |
| 2026-09-11 | 7159 |
| 2026-09-12 | 7165 |
| 2026-09-13 | 7171 |
| 2026-09-14 | 7174 |
| 2026-09-15 | 7183 |
| 2026-09-16 | 7191 |
| 2026-09-17 | 7204 |
| 2026-09-18 | 7208 |
| 2026-09-19 | 7217 |
| 2026-09-20 | 7219 |
Today
+2 stars today
This week
+48 stars this week
This month
+259 stars this month
Momentum
41.0
growth rate 0.67%/day
# Hiring Agent
<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>
<p align="center">
<a href="https://www.python.org/downloads/release/python-3110/">
<img alt="Python" src="https://img.shields.io/badge/python-3.11%2B-blue.svg">
</a>
<a href="https://github.com/interviewstreet/hiring-agent/blob/master/LICENSE">
<img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-yellow.svg">
</a>
<a href="https://github.com/psf/black">
<img alt="Code style: Black" src="https://img.shields.io/badge/code%20style-Black-000000.svg">
</a>
</p>
---
## Contents
- [Context and intent](#context-and-intent)
- [Coverage](#coverage)
- [Overview](#overview)
- [Architecture](#architecture)
- [Installation and Setup](#installation-and-setup)
- [Prerequisites](#prerequisites)
- [Quick setup with pip](#quick-setup-with-pip)
- [Ollama models](#ollama-models)
- [Configuration](#configuration)
- [How it works](#how-it-works)
- [CLI usage](#cli-usage)
- [Directory layout](#directory-layout)
- [Provider details](#provider-details)
- [Contributing](#contributing)
- [License](#license)
---
## Context and intent
This project got a lot of attention recently, and some of the discussion surfaced misconceptions worth addressing directly.
**What this is not:**
- Not an ATS (Applicant Tracking System)
- Not used to screen HackerRank's open roles
- Not a product available to HackerRank customers
**What it actually is:**
Every year HackerRank receives 50,000–60,000 intern applications. No human can read that many resumes well. This tool was built to *rank* them — helping decide which resumes to read first. Resumes scoring below the cutoff are filtered out, but the cutoff is intentionally set very low so only candidates at the very bottom of the distribution are removed. The vast majority pass through to human review, where the real decisions are made.
Since this was built, HackerRank has also shipped [AI Interviewer (Chakra)](https://www.hackerrank.com/products/ai-interviewer/) to automate the first round of interviews — so candidates are no longer assessed on their resume alone.
**On the default model:**
The repo ships with `gemma4:latest` as the default because it runs locally on most laptops without any cloud API key. Actual intern resumes at HackerRank are evaluated using a top-tier Gemini model. The repo ships with a demo config, not the production one.
---
## Coverage
Articles and discussions that have shaped how we think about improving this project:
| Article | Key takeaway |
|---|---|
| [HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74/100. No — 88/100. Actually 83/100.](https://danunparsed.com/p/hackerrank-open-source-ats) — *Dan Kinsky* | Deep statistical analysis of score variance across 100 runs of the same resume. Isolates which categories are stable (technical skills) vs. noisy (project quality judgments). Points to LLM non-determinism as the root cause. |
| [The Score Depends on the Roll of the Dice](https://pinggy.io/blog/hackerrank_open_source_ats_inconsistent_scoring/) — *Pinggy Blog* | Reproduces the variance findings and surfaces a security issue: invisible text embedded in PDFs can inflate scores significantly. |
| [The Hiring Rubric Inside](https://byteiota.com/hackerrank-ats-open-source-the-hiring-rubric-inside/) — *ByteIota* | Breaks down the scoring weights and argues that a GitHub-centric rubric disadvantages engineers whose work is in private enterprise repos. Also notes the signal degradation risk as candidates optimize for the now-public rubric. |
| [Analyzing resume scoring consistency](https://dev.to/mgobea/hackerrank-open-sourced-its-ats-analyzing-resume-scoring-consistency-1j5d) — *Mariano Gobea Alcoba, DEV Community* | Proposes concrete fixes: standardized data formats, versioned evaluation models, ensemble scoring, and explainabiliExcerpt of 13,743 characters
Read on GitHub
75
Anas Khan · @interviewstreet
16
2
2
2
2
1
1
1
1
1
1
1
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0a7e6d42aecba68e, desc:ai agent