Good news — the new company also provides laptops, and I got a Lenovo Xiaoxin 14 Pro with 32GB of RAM, the best-spec work computer I’ve had in 8 years.
The bad news is it has a glossy screen, and the office lights are so bright that the glare hurts my eyes. Luckily I also got a monitor, so I just use the external display (too bad the OLED has better colors…).
Every time I get a new machine, I used to configure SSH keys for GitHub to clone and push code. But I never bothered to keep track of the keys, so I ended up recreating them repeatedly. It wasn’t until I ran into multica and browsed the issue tracker that I realized GitHub provides GitHub CLI (gh) for quick authentication…
I maintain a package channel on prefix.dev to distribute some self-built packages. Since I’ve been busy with work recently, I haven’t looked after it for a while. Today I checked and noticed that the Actions had mysteriously stopped running… So I looked into the reason and decided to document a few other issues as well.
A few days ago, DeepSeek officially released the V4 preview, and this version really attracted a lot of attention. Rumors had been circulating since before the Chinese New Year. Since I happened to be leaving my job at the time, I didn’t get to try it out immediately. Now that I have some time, I integrated it with Opencode and Multica and wrote this blog post to test it out.
Today I came across an article from Qubit reporting that Anthropic just released Claude Managed Agents and already got an “open-source alternative” — this project is called Multica. I started using this project last week, so I did some digging.
Lately I’ve been deeply conflicted in my device selection, and after considering many devices, I have some thoughts I need to get off my chest.
Opencode has significantly improved my efficiency in development and bug fixing. However, in real work, I often need to maintain multiple projects simultaneously or handle development across several different directions. This means one person needs to manage and work on multiple branches at once. In such cases, manually switching branches, launching Opencode, confirming changes, testing, merging, and testing again can be quite tedious…
That’s why I’ve been looking for a task board tool where I can assign and track tasks through issues, letting Agents handle initial work while I focus on testing and reviewing code. Today I’m introducing Multica (https://multica.ai/), an open-source AI-native task management platform that aims to turn coding agents into real team members. Simply put, it allows you to collaborate with AI Agents the same way you would collaborate with human engineers.
Recently, I spent several days deeply experiencing multiple AI Agent products, from WorkBoddy, OpenClaw, LobeHub, DeerFlow2, LirbeChat, DingTalk Wukong to OpenCode, trying almost every tool I could find. Everyone has different needs, but my main focus is on open source and self‑deployable, feature completeness, and practical usability. Below is my personal comparison from a practical usage perspective.
Looking back, I learned to use FrontPage to create web pages since elementary school, but except for GitHub Pages, I never really set up and operated my own website. However, now it’s possible. With the support of agents and SaaS services, creating and launching a website has become quite simple…
I’ve been trying to use AI Agents / workflows to build efficient agent teams or AI workflows to improve productivity. After two weeks of experimentation, I’ve encountered several pitfalls…