{"name":"Tandemn","description":"Tandemn is an AI infrastructure platform for running inference workloads across heterogeneous GPU clusters. Tandemn schedules jobs, chooses an efficient hardware mix, and gives teams a simple CLI and server workflow for batch inference.","url":"https://docs.tandemn.com/","version":"1.0.0","protocolVersion":"0.3","preferredTransport":"HTTP+JSON","supportedInterfaces":[{"url":"https://docs.tandemn.com/","protocolBinding":"HTTP+JSON","protocolVersion":"0.3"}],"provider":{"url":"https://docs.tandemn.com/","organization":"Tandemn"},"documentationUrl":"https://docs.tandemn.com/","capabilities":{"streaming":false,"pushNotifications":false},"defaultInputModes":["text/plain"],"defaultOutputModes":["text/plain"],"skills":[{"id":"tandemn","name":"Tandemn","description":"Use when submitting batch inference jobs, managing GPU clusters, monitoring job progress, configuring the control plane, or optimizing hardware placement for LLM workloads. Agents should reach for this skill when users need to run inference at scale, reduce compute costs, or orchestrate work across heterogeneous GPU pools.","tags":[],"url":"https://docs.tandemn.com/.well-known/agent-skills/tandemn/skill.md"}]}