Armanc Keser_

Every few months there is a new kind of AI repo everyone is starring, ChatGPT wrappers in 2023, RAG and agent frameworks after that, MCP servers and coding agents in 2025, skills and agent managers in 2026, and I have starred a good chunk of all of them, so I got curious which ones are still alive. I pulled every repo created since January 2023 with more than 300 stars and one of the usual AI topics, 8,092 of them, had a model sort each one into a type from its name and description, and checked the last commit on each default branch as of November 7.

201 of the 668 chat apps came out in the first half of 2023 and 269 of the 563 MCP servers in the first half of 2025. 2026 is the year of skills, memory and agent managers: 409 of the 593 skill repos, 202 of the 313 memory ones and 182 of the 236 agent managers came out this year. Repos created after May 7 are too new to call quiet yet, so they get their own color.

Only 39% of the repos that came out in 2023 are still active as opposed to 72% of the 2025 repos. Even so, the 2023 chat apps are down to 33% and the 2023 model and training repos to 30%.

For years my computers had tons of problems I didn't understand. Games would stutter, things would lag, I just didn't have any idea what was going on, and if I restarted, magically sometimes things would be fixed. This time I couldn't restart, so Opus 5.5 and I had to find the actual problems: my wife's movie was being transcoded on the GPU, an NVIDIA Overlay process was sitting on 12.7 GB of memory, and two Razer services had left 32,709 zombie processes behind. Fixing those took Subnautica 2 from 2 FPS back to 60.

I started self hosting because of Immich, and I don't have a server with a good GPU, so my laptop (a Legion 5 with a 3070) became the server. These days the same laptop also runs Jellyfin, sits on top of the TV unit with a gajillion wires going into the back, and never gets turned off.

After a couple days of being on, I realized I was getting really bad performance. This was back when I was using Cursor, and with Cursor I figured out that Nahimic (the audio "enhancer" Lenovo preinstalls) was leaking memory through audiodg.exe, and an nssm.exe was leaking too (I never found out which service registered that one). I removed both from the auto start lists, and later on disabled Nahimic completely:

I don't have a Twitter account I use and I don't want the app, but Bluesky never took hold as the place the tech conversation happens, so people I know keep sending me x.com links anyway, from Slack and Signal and everywhere else. My method until now has been to tap the link, go up to the address bar, and add cancel after the x, which turns x.com into xcancel.com and gives me the tweet with no account and no app. It works fine. Doing it by hand a few times a week for a year is also exactly the sort of small friction that eventually annoys you into automating it, so I sent Claude off on a research mission.

What I wanted was the network-level version, one change on the Pi that already runs AdGuard, fixing every device in the house at once. That turned out to be considerably harder than I expected, and the reason it is hard is interesting enough to write down.

If you have not run into it, xcancel is a fork of Nitter, the old open-source Twitter frontend. It renders tweets as plain pages, no login, no app prompt, and it takes the same URL paths X does, which is why swapping the domain in the address bar just works.

I have been trying to get a feature into Jellyfin web for over a year. Opened three PRs, even got two approvals, but zero merges. The feature is relatively isolated and small. When you are adjusting subtitle offset in the player, it adds a timeline that shows you exactly which subtitle will appear when, so you can see what you are doing instead of guessing.

A reviewer gave detailed feedback on the first day. I split the work into smaller pieces when they asked, responded same day, changed the code style to match the project. The refactor PR got two approvals and is just sitting there. The smallest PR, 49 lines added, 0 deleted, has never gotten a single human review.

I brought this up in the Jellyfin community and someone joked that a year is not even that long for Jellyfin PRs. The main maintainer said the backlog "sucks... for everyone" and that every second he is not reviewing makes it worse. I asked if PR size limits, proposal requirements, different processes could help. The answer was mostly "there is only one maintainer."

I think there is more to it than that.

This is not unusual, most popular open source projects have the same problem.

I predict that in a year or so, the way people interact with and think about Skills will be vastly different, in that we will barely know or think about them. Skills are the latest buzz in the world of AI trend catchers, preceded by prompt libraries and multi-agents, and they solve a really important problem, which is progressive disclosure of know-how, letting agents dynamically load context based on the task at hand. But just like their predecessors, they fail some basic first principles in the long run.

Take prompt libraries, or GPTs as they used to be called, why did they fail? No one wants to write prompts, let alone maintain and improve them. We just want the agent we are talking to do the thing we want it to do, the way we want it to do it (preferably even better than what we imagine). Same thing with multi-agents, who wants to sit there thinking about whether a task should spawn a sub-agent or not? I just want the agent I am talking to, to do the task I give it as quickly and as thoroughly as possible.

Skills have the same fundamental problem. If we look at what they get used for, it's a handful of categories: sometimes they are a cache for anything an agent could find if it did some research (best practices for a React framework, how an API works, some source code analysis of a library), many times they hold user preferences on how they would like the agent to act, and most valuably they can capture some repeatable proprietary workflow that holds institutional knowledge (your company's deploy process, the exact sequence of Jira transitions your team decided on). The first two are mostly filling gaps that better models won't have, though there is still taste involved, choosing which best practices you subscribe to among many options isn't something a model can assume on your behalf. But that's exactly the kind of thing a good memory system should learn from working with you. I have Skills for different types of codebases, frontend and backend, and within those how I like the code to be for different languages, and that information fundamentally belongs in memory, not in files I have to manually curate. A model that has worked with me long enough to notice I always rewrite every resp to response and always reject inheritance for code reuse should just *learn that*, taste and all.