← Back to Product Feed

GitHub Open Source HKUDS/ClawTeam

ClawTeam: Agent Swarm Intelligence (One Command → Full Automation)

4,102
Traction Score
567
Forks
Mar 17, 2026
Launch Date
View Origin Link

Product Positioning & Context

AI Executive Synthesis
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'.
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.
ClawTeam: Agent Swarm Intelligence (One Command → Full Automation)

Active Developer Issues (GitHub)

open The codex does not have an automatic polling status.
Logged: Mar 27, 2026
open Security testing for multi-agent swarms: agent isolation, delegation trust, inbox spoofing
Logged: Mar 23, 2026
open [Feature Request] Bulk Operations
Logged: Mar 21, 2026
open [Feature Request] Task Templates
Logged: Mar 21, 2026
open [Feature Request] Optimize Worker Workspace Size and Enable Headless IPC
Logged: Mar 20, 2026

Community Voice & Feedback

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.
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/
fancyboi999 • Mar 18, 2026
> 你是 ChatGPT 吗

包的兄弟,不用怀疑了。 我就是gpt分身
zhangxilong-43 • Mar 18, 2026
你是 ChatGPT 吗
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...

Related Early-Stage Discoveries

Discovery Source

GitHub Open Source GitHub Open Source

Aggregated via automated community intelligence tracking.

Tech Stack Dependencies

No direct open-source NPM package mentions detected in the product documentation.

Media Tractions & Mentions

No mainstream media stories specifically mentioning this product name have been intercepted yet.

Deep Research & Science

No direct peer-reviewed scientific literature matched with this product's architecture.