Hands-on test of Multica’s multi-agent collaboration platform
Author 三金 tested Multica, a platform positioned as a customizable workspace where humans and AI agents can coordinate tasks. Following Multica’s official positioning, the platform also promises shared context and retention of discussions, records and outputs, although these capabilities were not independently established in the report. 三金 deployed the Web, API and PostgreSQL services with Docker Compose, then assembled four agents for a 3D rowing game. The game was completed in 1 hour 16 minutes, but the planned QA and playtest step was not performed. The report also describes a six-state task board, scheduled tasks, Web and desktop clients, and a desktop-launched CLI that detects locally installed AI coding tools.
The hands-on test documents a concrete deployment and multi-agent coordination workflow, including the time taken and the unperformed QA step. It also distinguishes observed functionality from capabilities stated in Multica’s official positioning, including automated development and reusable skills.
Hi~大家好，我是三金。
我最近在使用 VibeKankan 的时候发现它的版本已经很久不更新了！打开它的 Github 一看，竟然要停止维护了，最新版本还是我现在使用的 0.1.44，已经半年没更新过版本了！
最近一次的 commit 还是3 周以前，这就很难受，好担心它后面都没人维护。也想过直接拉源码改，但最终还是想拿来即用。故而又找到了另外一个平台——Multica。
能做什么
简单来说，这是一个可自定义多 Agent 协作的平台。
官方的定位 Multica 是一个人类和 AI Agent 共同工作的团队工作区，我们可以：
#Multica#VibeKankan#Multica Desktop#Multica CLI#PostgreSQL#Docker Compose#Blender