A
licenseB
qualityB
maintenanceEnables AI agents to submit GPU job requests, select eligible workers, track execution, and retrieve results via MCP.
14
21
MIT
agent-gpu-pool
by AlfredQuan
Related Servers
Alternatives to agent-gpu-pool
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to orchestrate multi-system LLM training, quantization, and evaluation workloads across local, Colab, Kaggle, and SSH targets, with persistent monitoring, historical analysis, and visualization via MCP tools.MIT
- FlicenseNot gradedqualityCmaintenanceProvides a durable SQLite-backed work queue for AI agents, enabling creation, claiming, starting, handing off, failing, and completing work items via MCP tools.-
- AlicenseAqualityBmaintenanceJungle Grid MCP Server lets AI agents submit, estimate, monitor, and retrieve logs for GPU workloads through Jungle Grid. It enables agentic execution for inference, training, fine-tuning, and batch jobs without manually choosing GPU providers or infrastructure.82 npm4MIT
- FlicenseNot gradedqualityCmaintenanceEnables MCP-aware agents to queue and run faster-whisper transcription jobs on a shared GPU, with tools to submit audio, poll job status, cancel jobs, and inspect queue status.-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to manage GPU training end-to-end through natural language, including submitting and scheduling jobs, monitoring logs and metrics, diagnosing failures, comparing runs, and recommending the best checkpoints.Apache 2.0
TDQS
B3/5.0
Scored across 13 tools
Disambiguation4/5
The tools separate into clear functional areas: job lifecycle, artifacts/results, and pool/quota administration. Slight overlap exists among list_jobs, list_ready_results, and get_project_runs, where run/result/job terminology could cause misselection, but the descriptions clarify the intended use.
Naming Consistency4/5
Almost every tool uses a verb_noun snake_case pattern such as submit_job, list_jobs, cancel_job, and fetch_artifact. pool_overview breaks the pattern as noun_noun, so the convention is consistent but not perfectly uniform.
Tool Count5/5
Thirteen tools is a well-scoped size for a GPU pool and experiment management server. Each tool covers a distinct workflow step with no obvious redundant entries.
Completeness4/5
The set covers the core experiment lifecycle: submit, list, get, cancel, logs, artifacts, and recorded results, along with worker and quota visibility. Minor conveniences such as a dedicated quota getter or result update tool are absent, but agents can accomplish the intended workflows with the current surface.
Maintenance
ActivityMaintained
ResponsivenessNo issues