{"skill":{"slug":"ollama-fleet-router","displayName":"Ollama — Herd Your LLMs Into One Smart Endpoint","summary":"Ollama fleet router — herd your Ollama LLMs into one smart endpoint. Route Llama, Qwen, DeepSeek, Phi, Mistral, and Gemma across multiple devices with 7-sign...","tags":{"apple-silicon":"1.0.0","deepseek":"1.0.0","fleet":"1.0.0","gemma":"1.0.0","inference":"1.0.0","latest":"1.0.0","llama":"1.0.0","llm":"1.0.0","load-balancer":"1.0.0","mistral":"1.0.0","multimodal":"1.0.0","ollama":"1.0.0","phi":"1.0.0","qwen":"1.0.0","routing":"1.0.0"},"stats":{"comments":0,"downloads":87,"installsAllTime":0,"installsCurrent":0,"stars":2,"versions":1},"createdAt":1774909848938,"updatedAt":1774915613912},"latestVersion":{"version":"1.0.0","createdAt":1774909848938,"changelog":"Ollama Fleet Router 1.0.0 — Initial Release\n\n- One smart endpoint for routing LLM requests across multiple Ollama devices, with drop-in OpenAI SDK compatibility.\n- Advanced fleet scoring: routes requests based on VRAM, model availability, queue depth, latency, and more (7-signal scoring).\n- Robust auto-retry, VRAM-aware fallback, and context protection for reliable and efficient operation.\n- Supports image generation, speech-to-text, and embeddings, all via the same endpoint.\n- Real-time dashboard for monitoring fleet health, usage, models, and workloads.\n- Includes project-based request tagging and strict guardrails for safety.","license":"MIT-0"},"metadata":{"os":["darwin","linux"],"systems":null},"owner":{"handle":"twinsgeeks","userId":"s17dgy27g44azc3tday4qh394d83ensj","displayName":"Twin Geeks","image":"https://avatars.githubusercontent.com/u/261838102?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.2.0","updatedAt":1774915613912}}