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.

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.

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.

Compared to two years ago at my previous company, I now use AI much more frequently. If the limitation back then was the convenience of the tools themselves, the current limitation seems to be my own knowledge and technical skills rather than AI.

This year, DeepSeek has made LLMs popular again. Although after ChatGPT, Copilot and Cursor have been advertising everywhere, I never actually tried them… So this year, I… tried Cline, which is indeed good, but also matches my preconception - not that convenient. Especially since I need something that can be used directly in the command line and quickly integrated into scripts to batch complete some simple coding initialization tasks. That’s how I found aider…

This title is a bit too nested… but the fact is, I suddenly felt capable! I finally have a chance to become a full-stack developer! To showcase my capabilities enhanced by chatGPT, I decided to develop a tool that uses chatGPT to read papers (I’ve also considered using it for meta-analysis).