Top 10 that week
-
3 use cases
REPO
pbakaus/impeccableImpeccable
A design skill pack for coding agents: commands like polish, bolder, critique and audit steer the look of a page, review it for usability and accessibility, and catch generic AI design before it ships.
Why it's hot +10,921 stars this week, 104k total, picked up by one AI source we track · Rust
Who should care Developers who build front ends with Claude Code, Cursor, Codex or other agents and want less generic looking pages.
-
5 use cases
REPO
mattpocock/skillsSkills
A small set of reusable instructions that make coding agents work like a careful senior engineer instead of guessing.
Why it's hot +9,238 stars this week, 315k total, picked up by one AI source we track · Shell
Who should care Developers who use AI coding tools daily and want more reliable output.
-
4 use cases
REPO
thedotmack/claude-memClaude Mem
A memory plugin that captures what your coding agent does in each session, summarizes it, and feeds it back in later sessions so the agent keeps project context.
Why it's hot +8,822 stars this week, 113k total, picked up by one AI source we track · TypeScript
Who should care Claude Code and other coding agent users tired of re-explaining their project every session.
-
3 use cases
REPO
Nutlope/hallmarkHallmark
Hallmark is a design skill from Together AI for Claude Code, Codex, Cursor and OpenCode that builds pages that do not look AI-generated.
Why it's hot +7,622 stars this week, 49k total, picked up by one AI source we track · CSS
Who should care Builders who use coding agents for landing pages and sites and are tired of the same generic AI look.
-
3 use cases
REPO
HKUDS/DeepTutorDeep Tutor
An open-source AI tutoring app with learning paths, assessments, notebooks, narrated video lessons and tutoring memory, plus a CLI for agents.
Why it's hot +7,512 stars this week, 55k total · Python
Who should care Students, teachers and builders who want a personalized AI tutor they can run themselves.
-
4 use cases
REPO
milind-soni/OpenMausBotOpen Maus Bot
OpenMausBot is an open-source chat app where each bot is a local Claude, Codex or Grok agent with its own model, cloud computer and connected apps.
Why it's hot +5,847 stars this week, 13k total · TypeScript
Who should care Solo operators and small teams who already use Claude, Codex or Grok and want a roster of chat-based bots that ask before they act.
-
5 use cases
REPO
tashfeenahmed/freellmapiFreellmapi
A self-hosted server that combines the free tiers of 34 LLM providers behind one OpenAI-compatible /v1 endpoint, with smart routing, automatic failover on rate limits, per-key usage tracking, and encrypted key storage.
Why it's hot +4,388 stars this week, 48k total · TypeScript
Who should care Developers who want to experiment with many models through one API without paying, and who are willing to manage their own provider keys.
-
3 use cases
REPO
multica-ai/andrej-karpathy-skillsAndrej Karpathy Skills
A single CLAUDE.md file with four principles for Claude Code: think before coding, simplicity first, surgical changes and goal driven execution.
Why it's hot +3,808 stars this week, 230k total
Who should care Claude Code users who want fewer silent assumptions, less bloated code and fewer edits outside the task.
-
5 use cases
REPO
calesthio/OpenMontageOpenMontage
OpenMontage is an open-source system that lets an AI coding assistant plan, generate, edit, and render videos from plain-language requests through 12 production pipelines.
Why it's hot +3,743 stars this week, 77k total · Python
Who should care Creators, marketers, and developers who want an AI coding assistant to produce finished videos from a written request.
-
3 use cases
REPO
AgriciDaniel/claude-seoClaude SEO
A free SEO plugin for Claude Code that runs a full site audit with 26 sub-skills and 19 agents and returns an action plan sorted by what matters most.
Why it's hot +3,531 stars this week, 27k total, picked up by one AI source we track · Python
Who should care Site owners and marketers who use Claude Code and want technical SEO, schema and AI search checks in one run.
Past weeks
How we rank
Every day we snapshot star counts for a few hundred repos from GitHub's trending lists and the newest AI projects, keep only AI projects, and score each one on star growth, how many of the AI newsletters, forums and feeds we read are talking about it, and how new it is. Then we read each README and sum it up in one plain sentence. Star farms and sketchy projects get dropped.