GIT_FEED

// INSIGHTS

Data-driven intelligence from every public GitHub repo. Weekly rankings, breakout signals, and trend analysis — so you see what's moving before everyone else.

WEEKLYWeek of Apr 19, 2026

RISING THIS WEEK

// WEEKLY_RANKING

The 10 fastest-accelerating repos on GitHub right now, ranked by 7-day star velocity with week-over-week momentum.

1
forrestchang/andrej-karpathy-skills

This project provides a single configuration file that makes Claude, Anthropic's AI coding assistant, behave more like a careful senior engineer — asking questions before diving in, keeping code simple, and only touching what it's supposed to touch. It translates AI researcher Andrej Karpathy's widely-shared frustrations about AI coding tools into practical guardrails you can drop into any project in seconds.

+39.9k stars74.0k total
2
NousResearch/hermes-agent

Hermes Agent is an AI assistant that gets smarter the more you use it — it remembers past conversations, learns new skills from experience, and builds a profile of who you are over time, all without being tied to any single AI provider or device. It runs in the cloud and connects to messaging apps like Telegram, Slack, and WhatsApp, so you can interact with it anywhere while it handles complex tasks in the background.

+24.7k stars109.2k total
3
JuliusBrussee/caveman

Caveman is a plugin for Claude Code (Anthropic's AI coding assistant) that makes the AI respond in simplified, stripped-down language — like a caveman — slashing the number of words and billable tokens the AI uses by up to 75% while preserving all the technical accuracy. It's essentially a compression trick for AI conversations, making every coding session faster and cheaper without sacrificing the quality of answers.

+12.8k stars42.7k total

View full ranking →

// COMING_SOON

Breakout Repos

Projects that crossed critical thresholds this month — from unknown to 1k stars, from 1k to 10k.

Monthly AI Code Report

Deep-dive into AI coding tool adoption, market share shifts, and what the commit data reveals.

Category Movers

Which categories are heating up and which are cooling down, backed by aggregate signal data.