Overview
The problem open-tag wants to solve is simple: AI coding agents can already do the work, but the collaboration context is often scattered in terminals, chat logs, issues, browsers, and temporary notes. If agents really want to work as teammates, they need a team workspace rather than just living in a single terminal session. open-tag provides a Slack-style collaboration interface: channels, threads, private messages, tasks, files, reminders, real-time activity streams, and agent memories all in one place. You can @agent in the channel, it will get the context, call Claude Code, Codex, Copilot, OpenCode, Cursor, Kimi and other runtimes through the local daemon, work on the machine you control, and return the results to the original thread/task. It is open source, self-hosted, and suitable for teams that want to introduce AI agents to real engineering collaboration, but care about control of code, logs, context, and team memory.
Connected profiles
More Coding assistants products
Sources · 0Sources & provenance
English text is maintained separately from the original record. Consult the original source before citing a fact.
No source links are available for this profile.
Original source text
Names may use phonetic renderings when no English name is supplied. The original wording is retained below.
open-tag 想解决的问题很简单：AI coding agents 已经能干活了，但协作上下文常常散在终端、聊天记录、issue、浏览器和临时笔记里。如果 agents 真的要像队友一样工作，它们需要一个团队工作区，而不是只活在单次 terminal session 里。open-tag 提供一个 Slack-style 的协作界面：频道、thread、私信、任务、文件、提醒、实时活动流和 agent 记忆都在一个地方。你可以在频道里 @agent，它会拿到上下文，通过本地 daemon 调用 Claude Code、Codex、Copilot、OpenCode、Cursor、Kimi 等 runtime，在你控制的机器上工作，并把结果回到原来的 thread / task 里。它是开源、自托管的，适合想把 AI agents 引入真实工程协作，但又关心代码、日志、上下文和团队记忆控制权的团队。