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.

With the global hype around OpenClaw, I’ve once again pondered a bit: is the current agent frenzy really because AGI has arrived? I naturally don’t think so.

Last time I successfully packaged my own program, so I wanted to try something else. Recently opencode has been extremely popular, and I’ve been using it too. Since it’s not yet available on conda, I decided to package it.

It all started when I tried to use Devpod to set up a container based on Docker Compose, only to find that Devpod didn’t seem to be able to call Docker Compose correctly to create the container. I didn’t think much of it until I searched online… Wait, what? Has this project really been dropped by loft‑sh?

Finally, aider-chat is available as a conda package, which means it can theoretically be installed globally via pixi global. However, during actual installation, you’ll find that one of its dependencies, tree_sitter_languages, doesn’t have a corresponding aarch64 version, causing the installation to fail. This made me wonder: could I rely on AI to solve this?

Those Bioinfo projects at my new workplace are mostly personalized, so each project inevitably involves reading some new papers. Once again, I’ve been feeling a headache from reading so many english papers. It occurred to me that the last time I created a word cloud was back in 2022. Three years have passed, and it’s time to welcome… well, just an update.

From late 2022 to early 2023, ChatGPT exploded in popularity, and I started using LLMs to assist with script writing. Although it was quite useful, the price was relatively high, and payment was always an issue, so its application was limited to simple coding problems.

From late 2024 to early 2025, DeepSeek became a hit. While its answers often weren’t entirely satisfactory, and the addition of a “thinking mode” made the response time a bit slower, it was really cheap! A year later, DeepSeek remains one of the most affordable models in terms of tokens while still delivering decent output. I paid 50 RMB at the beginning of the last year, and now, almost exactly a year later, I still have 27 RMB left… As a result, I’ve become much bolder in applying LLMs to various other areas.

I’ve been using my current avatar for over ten years. Ever since I started working in bioinformatics, I’ve wanted to add more complexity to it—half with circuit‑board patterns, the other half with DNA patterns, connected by a smooth transition in the middle to symbolize the transformation from biology to information, which fits my professional field. However, I’m not very skilled at photo editing, so I couldn’t achieve the desired effect. This year, the newly released image‑editing models gave me hope to realize my idea.