← Back to AI Insights
Gemini Executive Synthesis

Agent communication between multiple devices in ClawTeam.

Technical Positioning
Achieving cross-device, intranet-based agent communication for complex collaborative workflows (e.g., interface integration, PRD co-editing) to deliver 'Full Automation' via 'Agent Swarm Intelligence'.
SaaS Insight & Market Implications
This issue highlights a critical functional gap in ClawTeam's 'Agent Swarm Intelligence' promise: the lack of explicit multi-device, intranet-based agent communication. Developers are seeking capabilities for complex, real-world B2B scenarios like cross-device interface integration and collaborative document editing among specialized agents. The inability to support such foundational inter-agent communication across devices severely limits the 'Full Automation' value proposition. Without this, ClawTeam remains a single-device orchestration tool, failing to address distributed team workflows. This represents a significant barrier to enterprise adoption where collaborative, multi-agent, cross-device operations are standard.
Proprietary Technical Taxonomy
Agent communication multiple devices intranet CC OpenClaw interface integration testing backend agent frontend agent

Raw Developer Origin & Technical Request

Source Icon GitHub Issue Mar 18, 2026
Repo: HKUDS/ClawTeam
Does it support Agent communication between multiple devices? 多设备间的 Agent 通信是否支持？

内网多台设备的多个Agent（CC、OpenClaw...） 之间可以通信吗？
案例1：接口联调时后端agent提供完接口，前端agent给出接口修改建议。他们之间可以跨设备沟通吗？
案例2：修改后的prd文档要同时分发给后端、前端、测试。然后这些 agent 之间还要各自提意见，共同编辑，类似于多人协作的word文档的场景。这个Team模型能支持吗？

Can multiple agents (CC, OpenClaw, etc.) on multiple devices within an intranet communicate with each other?
Case 1: During interface integration testing, the backend agent provides the interface, and the frontend agent provides suggestions for interface modifications. Can they communicate across devices?
Case 2: The modified PRD needs to be distributed simultaneously to the backend, frontend, and testing teams. Then, these agents need to provide their own feedback and collaboratively edit the document, similar to a multi-person collaborative Word document scenario. Can ClawTeam support this?

Developer Debate & Comments

fancyboi999 • Mar 18, 2026
我翻了下当前实现，先给一个不绕的结论： 不是完全不支持，但也不能简单理解成“多设备之间已经像多人协作文档那样完整打通了”。更准确地说，**消息通信这层有跨设备能力的基础版，团队状态这层仍然强依赖共享目录**。 我看的是这几块代码： - `clawteam/team/mailbox.py` - `clawteam/transport/file.py` - `clawteam/transport/p2p.py` - `clawteam/team/manager.py` - `clawteam/team/tasks.py` - `clawteam/board/collector.py` 具体拆开说： 1. **消息层** `MailboxManager` 下面走的是 `Transport` 抽象，现在已经有 `FileTransport` 和 `P2PTransport`。 `P2PTransport` 用的是 ZeroMQ PUSH/PULL，在线时可以直接发，发不通就回退到文件投递。所以“后端 agent 给前端 agent 提建议、互相发消息”这件事，本身是有能力基础的。 2. **状态层** 团队配置、任务、事件日志、看板统计这些状态，还是落在 `CLAWTEAM_DATA_DIR`（默认就是 `~/.clawteam`）下面的 JSON 文件里。 也就是说，**就算消息能发过去，如果多台机器看不到同一份 team/task/state，它们也不算真正处在同一个 Team 视角里**。 3. **P2P 也不是完全脱离共享目录** 这一点很关键。当前 `P2PTransport` 里的 peer discovery 还是靠 `teams//peers/*.json`。所以它解决的是“消息怎么实时传”，不是“整套团队状态怎么跨机器同步”。 所以按你举的两个场景，更准确的回答是： - **案例 1：接口联调，前后端 agent 跨设备沟通** 可以支持，但前提是多台机器至少共享同一个 `CLAWTEAM_DATA_DIR`（比如 NFS/SSHFS），或者你自己额外补一层状态同步。否则只能算“消息能通”，还不算完整协作。 - **案例 2：PRD 分发给前后端和测试，再分别提意见、协同推进** 这种“分发 + 收集反馈 + 任务协...
zhangxilong-43 • Mar 18, 2026
你是 ChatGPT 吗
fancyboi999 • Mar 18, 2026
> 你是 ChatGPT 吗 包的兄弟，不用怀疑了。 我就是gpt分身
guhuajun • Mar 19, 2026
> > 你是 ChatGPT 吗 > > 包的兄弟，不用怀疑了。 我就是gpt分身 **不绕** 是最近ChatGPT的回答灵魂。我觉得有一天这个项目会用上 redis。 顺便域名已经被捷足先登了 https://clawteam.com/
tjb-tech • Mar 30, 2026
Current status: cross-device agent communication is partially supported, but full distributed team state is not yet first-class. - Messaging: supported via the `p2p` transport (`clawteam.transport.p2p`), so agents on different machines can exchange messages. - Team/task state: still primarily relies on shared `CLAWTEAM_DATA_DIR` state, so this is not yet a fully self-contained multi-device collaboration model. - Collaborative-document style editing: not a native capability today; the current model is closer to shared files/Git + inbox/task coordination. So for the question in this issue, the answer is `partially yes`, but not in the fully distributed / real-time collaborative sense yet. I would keep this issue open as tracking for first-class multi-device team state and collaboration semantics.

Adjacent Repository Pain Points

Other highly discussed features and pain points extracted from HKUDS/ClawTeam.

Extracted Positioning
Optimization of worker workspace size and enablement of headless IPC for ClawTeam
Scalable, efficient, and robust multi-agent swarm intelligence
Extracted Positioning
Reusable task templates for common workflows in ClawTeam
Standardized and consistent multi-agent task execution
Extracted Positioning
Bulk operations (update/delete) for tasks in ClawTeam
Efficient management of multi-agent swarm tasks
Extracted Positioning
Security vulnerabilities in multi-agent swarm intelligence architecture
Secure, autonomous multi-agent system for full automation
Extracted Positioning
Lack of automatic polling/persistent status for Codex agents after task completion.
Enabling continuous operation and persistent interaction for AI agents, moving beyond single-shot task execution towards "Full Automation" and "Agent Swarm Intelligence."

Engagement Signals

5
Replies
open
Issue Status

Cross-Market Term Frequency

Quantifies the cross-market adoption of foundational terms like OpenClaw and CC by tracking occurrence frequency across active SaaS architectures and enterprise developer debates.