Configure budget cloud and local Ollama AI models with smart routing.
npx skills add https://github.com/davekilleen/Dex --skill ai-setup-davekilleen
Please help me install this Agent Skill. Skill: ai-setup Source: https://github.com/davekilleen/Dex/tree/main/.claude/skills/ai-setup Command: npx skills add https://github.com/davekilleen/Dex --skill ai-setup-davekilleen
This Skill helps users reduce AI costs by configuring cheaper cloud models and enables offline AI functionality using local models, providing flexibility and cost savings.
Run /ai-setup to configure your AI model options for cost savings and offline use.
High-intent search queries and answers about installing and using this skill.
Reduce AI model costs and enable offline operation by configuring budget cloud providers and local Ollama instances. This setup manages API keys and model downloads to dynamically route tasks between premium, budget, and offline models.
Smart routing dynamically selects AI models by evaluating task complexity, cost, and internet availability. It automatically switches between premium Claude, budget cloud options, and local offline models based on current connectivity and requirements.
Yes, you can use local Ollama models for offline AI tasks without an internet connection. This Skill configures local model downloads and system settings, allowing full AI functionality during travel or when network access is unavailable.
Yes, OpenRouter supports budget cloud models for cheaper AI tasks. Integrating with OpenRouter allows access to significantly cheaper models like Kimi and DeepSeek, drastically cutting expenses for online AI operations.
The best way to manage AI API keys and model configurations is using an automated setup tool. It centralizes API key management, handles local model downloads, and configures system settings for seamless switching between cloud and offline environments.
Use offline AI models instead of budget cloud providers when you lack internet connectivity, such as during travel, or when strict data privacy is required. Budget cloud models are better suited for connected workdays to save on premium API costs.
hemoryConfigure budget cloud and local AI models with smart routing.
latestaiagentsRoute LLM tasks to models based on complexity, cost, and latency.
kk20300113-pngRoutes LLM API tasks by complexity with budget tracking and retry limits.
AveerOrchestrate deployment and configuration of local LLM inference servers for OpenCode.
