Query local and cloud AI models across multiple providers.
npx skills add https://github.com/phyter1/seed --skill fleet-inference
Please help me install this Agent Skill. Skill: fleet-inference Source: https://github.com/phyter1/seed/tree/main/.claude/skills/fleet-inference Command: npx skills add https://github.com/phyter1/seed --skill fleet-inference
This Skill enables direct querying of any model within a fleet, whether local or cloud-based, reducing latency and simplifying model access for AI tasks.
Query models by specifying a prompt or list all available models, enabling quick integration into AI workflows.
High-intent search queries and answers about installing and using this skill.
Query multiple local and cloud AI models by sending prompts to specific endpoints or using auto-routing to dynamically select the best available provider for your inference tasks. This simplifies large-scale generation and analysis across diverse deployment environments.
Yes, this approach supports both local and cloud providers including MLX, Ollama, Cerebras, Groq, Gemini, and OpenRouter. It ensures secure, conditioned access to AI endpoints for enterprise or personal use cases across these diverse environments.
The best way to run large language model inferences across a fleet is by facilitating direct and flexible access to multiple local and cloud models. This reduces latency and optimizes performance through dynamic model selection.
Yes, you can auto-route prompts to the best available provider for on-demand inference tasks. This flexible querying mechanism supports dynamic model selection to optimize performance for inference, analysis, and generation.
Switching between local and cloud model endpoints does not present major limitations here, as the system is designed to simplify model access and reduce latency. It ensures secure, conditioned access to AI endpoints across diverse deployment environments.
winsorllcConnect to local LLM endpoints with automatic cloud fallback.
shynlee04Search the web and extract content via Tavily and Exa using the inference.sh CLI.
Lightning-AIAutomate deployment and lifecycle management of containerized services on Lightning AI.
traylinxRoute AI model requests across providers via a local endpoint.
