Smart Router for Ollama

Intelligent task routing between local and cloud Ollama LLM instances. Use when the user wants cost-efficient AI responses by routing simple tasks to a local...

This skill appears to do what it claims, but take these precautions before installing or using it: 1) Inspect and update config/router.yaml so any cloud base_url points to servers you control or trust (replace placeholder addresses). 2) Be aware that prompts, conversation history, classification results, model availability, and health checks are stored locally (cache/*.db, logs/router.log); disable or clear caching/logging if you don’t want persistent records. 3) Run the code in a controlled environment or sandbox if you will route sensitive data to remote endpoints. 4) If you don't want automatic web-search integration, ensure search integration is disabled or absent. 5) Review network policies if you must prevent the skill from contacting external hosts.

Type: OpenClaw Skill Name: ollama-smart-router Version: 1.0.0 The ollama-smart-router skill bundle is a legitimate utility designed to route LLM tasks between local and remote Ollama instances based on task complexity. The code implements heuristic classification using regex (scripts/classify.py), maintains state via SQLite-based caching and conversation memory (scripts/cache.py, scripts/conversation.py), and includes a system profiler (scripts/system_profiler.py) that uses standard system commands (e.g., nvidia-smi, sysctl) to detect hardware capabilities. No evidence of malicious intent, data exfiltration, or prompt injection was found; the functionality is transparent and aligns with the documentation.