Manage OpenI resources with natural language for login, jobs, nodes, and logs.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "qzcli" yet — see the docs or source repo.
Log in to the OpenI platform and list the currently available compute nodes, grouped by GPU count and idle status.
Returns the login result and an available node list or summary table for choosing a runtime environment.
Submit a training job on OpenI: use 2 GPUs, the pytorch image, and the startup command python train.py, then return the job ID.
Creates and submits the job, then returns a config summary, submission status, and job ID.
Check the latest status of job ID job-12345 and show the most recent 100 log lines.
Returns the current job status, key runtime details, and recent logs to help troubleshoot issues.
Query and manage OpenNMS alarms, nodes, events, and assets in plain language.
Read and manage openQA jobs, machines, and test suites via REST API.
Query open data platforms in natural language with a plugin-based MCP server.
Manage Kubernetes clusters with natural language for diagnostics, logs, and scaling.
Diagnose OpenClaw node pairing, auth, routing, and connection issues.
Delegate tasks from Claude Code to OpenCode subagents and retrieve results asynchronously.