For those who forgot to bring sparklers, didn’t buy fireworks, or simply prefer a digital experience.

Happy New Year 2026!

I predict we will be able to use useful enough models on our own consumer machines with decent tokens per second and we will see an open source alternative to Claude Code using this setup, essentially making agentic vibe coding free.

I’m building an open-source Electron desktop app for managing Claude Code, allowing users to configure various settings on user/project level, setup MCP servers, subagents, skills, see usage metrics and more https://antonbelev.github.io/claude-owl/

Hi all,

I just finished adding support for Windows in the latest version of Claude Owl (it also supports MacOS).

I've (mostly) vibe-coded this Electron App with the goal of making most of Claude Code. I found having to configure so many various settings from the terminal overwhelming and hard.

I've also recently added metrics showing you your daily usage, tokens generated, model usage and more.

The project is open source and completely free https://github.com/antonbelev/claude-owl

Full features list with screenshots you can find here https://antonbelev.github.io/claude-owl/screenshots.html.

The tool is still in Beta, so there will be warnings on Mac and Windows if you try installing the binaries since they are not signed, that's expected (see installation guide).

What you can do as a user is - fork the repo and run it locally with

`npm run dev:electron` in case you prefer not to download the binaries.

I'd love your feedback!

I started working on Claude Owl last week as a personal project to stop manually editing JSON files whenever I need to tweak Claude Code settings. Basically, it's an Electron app that gives you a visual interface for managing agents, skills, hooks, debug logs, and permissions rules instead of doing it all in your text editor.

At first it was just for me, but I figured why not throw it on GitHub and see what people think. It's MIT licensed and fully open source: https://github.com/antonbelev/claude-owl

## Current state

Pretty functional on macOS (Intel & Apple Silicon). I built out: - Subagents manager (create/edit/delete with custom system prompts) - Settings editor (environment variables, permissions rules, core config) - Skills & plugins browser - Debug logs viewer - Hooks manager (read-only)

## Honest caveats

- Only tested on macOS – Windows/Linux support is on my radar but haven't touched it yet - It's mostly "vibe-coded" – built to solve my own pain points. Code quality is decent but it's not enterprise-grade - Still in beta, still iterating

## What I'm actually asking

- Would you find this tool useful too? - What are your biggest pain points in configuration management for Claude Code? - What features or ideas would you want me to add if you were to use Claude Owl?

Appreciate your feedback.

Anton

OAuth handshake still gives internal server errors when you try to /login from Claude Code

My auth token expired and when I type /login in Claude Code it leads me to a webpage showing:

OAuth Request Failed Internal server error

This has 100% ruined my morning! -_- I tried many different ways to get in, I'm using claude in terminal in cursor.

Fix for me: Hopefully will work for you guys too, I logged out of claude, restarted cursor, used the anthropic console login method instead of normal login, when you click the link it gives you an option to signin with chat credentials instead, there it did not work, I pressed the link given in claude a few times and kept trying, finally I was given a pastable code, this took a while to be accepted in terminal but now is logged in.

hope it works for someone else aswell!!

tried, not working for me...

Damm... Sorry to hear it, I was watching console during my attempts, see many errors on multiple attempts, the one that worked did not show any console error logs on the working attempt if that helps

they marked as resolved but is not Resolved This incident has been resolved. Posted 30 minutes ago. Oct 31, 2025 - 10:36 UTC Update We are continuing to monitor for any further issues. Posted 30 minutes ago. Oct 31, 2025 - 10:36 UTC Monitoring A fix has been implemented and we are monitoring the results. Posted 1 hour ago. Oct 31, 2025 - 09:46 UTC Identified The issue has been identified and a fix is being implemented. Posted 2 hours ago. Oct 31, 2025 - 09:30 UTC Update We are continuing to investigate this issue. Posted 2 hours ago. Oct 31, 2025 - 09:25 UTC Investigating We are currently investigating this issue. Posted 2 hours ago. Oct 31, 2025 - 09:17 UTC This incident affected: claude.ai, platform.claude.com (formerly console.anthropic.com), and Claude API (api.anthropic.com). https://status.claude.com/incidents/s5f75jhwjs6g

Until it's back up and running, something I did that worked for me was access the web version of Claude Code, link the repository there, and ask them to implement something. After they implemented it, they enabled the option to click the "Open in CLI" button, allowing me to use Claude Code CLI from the terminal again.

And it's expiring a lot lately. I used to go weeks without it expiring, yesterday it expired twice in one day.

I just managed to log in to claude code. You have to spam the login when you recive the screen with authorize press on it multiple times. you will recive errors than try again i have tried like 70 times and it started finnaly

it worked for me as well, thanks

haha worked for me!

This is the day I decided to finally sign up and use claude-code - and then I'm greeted with this exact page. Gahhh!

welcome

Still down for me. Anyone got a workaround?

Nope only with cursor for the moment

Related question: why does Claude Code need a new auth token very few days?? It's so annoying.

Ah so it's not just me. What's a good backup these days? Gemini? GLM?

try cursor with auto its more stupid but does the work

Ended up going with Z.AI because it's a drop-in replacement. Back in business for now.

you can use it in terminal?

Yeah, I'm using it with Claude Code. It continued where I left off as well (using the `--resume` flag)

It's not as smart as Opus by the way. Seems to match Sonnet.

Edit: See here, they've got an anthropic-compatible endpoint for this purpose - https://docs.z.ai/devpack/tool/claude

Same here, happed after updaing claude code to 2.0.30 today.

Same with me, is smth happened with claude?

how long that outing is gonna take ! it's been like an hour!

it works for me now

same here, and I had a lot of work to do....

happening to me as well right now

+1

same problem here

same for me

Same here, paying £90 for a subscription I can hardly use FFS

Same shit.. paying 200 a month for nothing - just cancelled.

same here

same here

same

same here

same

same...

same

same here

This is now fixed, I forgot to change the visibility setting to public for the Gitlab Pages of the demo project, thank you for reporting it https://antonbelev.gitlab.io/beblob-demo/

Apologies, looking to fix it now! In the meantime the widget is visible on any blog post on my personal blog e.g. https://belev.me/2025/02/13/hexo-bluesky-feed-is-now-an-offi... - The demo page intends to also show the different themes and allow the user to switch between them. Will get it sorted asap.

I'm using it as a leverage for my side-project ideas. I was making excuses not to make open-source projects for years because of not having enough time.

Last week alone I launched two mini side projects, apparently using "code vibing" technique. Didn't know what I was doing had a name. - https://github.com/antonbelev/llm-fuse and https://github.com/antonbelev/hexo-bluesky-feed if you are interested.

I feel LLMs open the productivity door for me. Especially, outside my day-to-day work.

Yes, the tools I've built are not using the best practise, they may have little bugs here and there, but at least I can iterate quickly over my ideas, and get something out there.

So far I'm focusing on tools which I know at least I will be using for my personal blog.