Zhijiangyun Cloud (智匠云)
cloud.artibotPublished by artibot.cloudOfficial publisherv1.0.1Updated Oct 25, 2026
Robot embodied-AI cloud for GPU training, inference, benchmarks, and robot data collection.
Overview
A remote ArtiBot Cloud (Zhijiangyun) endpoint that gives an assistant access to an embodied-AI robot cloud for GPU training, inference, benchmarks and robot-emb
- What you can do
- Connects the assistant to the Zhijiangyun embodied-AI cloud platform over a remote HTTP endpoint, authenticated with an API key. The manifest lists no tools, so the exact operations are not documented here; the platform is described as covering GPU training, inference, benchmarks and robot data collection. The public README is a documentation index for embodied episode data formats, a synthetic episode example with a local validator, robot training data notes and a scene-capture guide, and it states that production source code, deployment infrastructure, customer data, private robot-control interfaces, credentials and non-public model weights are not published.
- When to use it
- Consider it when you already work with the Zhijiangyun/ArtiBot Cloud platform and want an assistant to reach its robot-learning resources, such as training, inference or benchmark workflows, from a chat client. It is not useful without a platform API key, and the available operations are not described in the listing.
- Requirements
- A remote streamable HTTP endpoint; no local package or runtime is needed. A Zhijiangyun API key with the zj_ext_ prefix is required, issued through the platform's key page, and sent as a bearer token in the Authorization header. Network access to the endpoint is required.
Installation
In SourceWeft
- Open Zhijiangyun Cloud (智匠云) in the dashboard and add it to a workspace.
- Connect Authorization token credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/cloud.artibot%2Fzhijiangyun/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"zhijiangyun-cloud": {
"type": "http",
"url": "https://mcp.artibot.cloud/mcp",
"headers": {
"Authorization": "Bearer <YOUR_TOKEN>"
}
}
}
}README
ArtiBot Cloud Public Resources
English
What this repository is
This repository is the public technical-resources index for ArtiBot Cloud, an embodied-AI platform. It is being developed as a home for reusable documentation, data-format references, synthetic examples, and independently releasable open-source components.
The first public materials focus on a practical question that appears across robot-learning workflows: how to describe one complete observation–action–outcome episode in a portable, inspectable format.
Start here
What is not published here
This repository does not publish production platform source code, deployment infrastructure, customer data, private robot-control interfaces, credentials, or non-public model weights. A document or example in this repository is not a promise that the corresponding hosted platform capability is publicly available.
Reuse and licensing status
No repository-wide license is granted at this stage. Before reusing any material, check whether the individual file provides an explicit license or permission notice. The licensing of future code, documentation, images, videos, datasets, and model assets will be stated separately and only after their provenance and reuse rights have been verified.
Official platform
For the hosted platform, visit www.artibot.cloud.
中文
这个仓库是什么
本仓库是 ArtiBot Cloud（智匠云） 的公共技术资料索引，后续将逐步发布可复用的文档、数据格式参考、合成样例以及边界明确的独立开源组件。
当前首批公开材料聚焦于具身智能训练中的一个基础问题：如何用可移植、可检查的格式描述一条完整的“观测—动作—结果”交互 episode。
建议从这里开始
本仓库不公开什么
本仓库不公开生产平台源代码、部署基础设施、客户数据、私有机器人控制接口、凭据或未公开模型权重。本仓库的文档和样例不代表对应的托管平台能力已经对外开放。
使用与授权状态
本阶段不授予仓库范围内的统一许可证。在复用任何资料前，请检查具体文件是否包含明确的许可证或授权说明。未来的代码、图像、视频、数据集和模型资产会在确认来源与再利用权利后分别标注授权范围。
官方平台
如需了解托管平台，请访问 www.artibot.cloud。
Repository status
The public documentation and examples in this repository are evolving. Please open an issue only for material that is already public in this repository; do not include credentials, private data, or production-system details in an issue.
本仓库的公共文档与样例会逐步完善。Issue 仅用于讨论本仓库已经公开的内容；请勿在 Issue 中提交凭据、私有数据或生产系统细节。
Source: README.md at commit b8f007b
Tools
0Version history
1- v1.0.1LatestSep 16, 2026
Score
75% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.