$ loading_
Route and manage multi-model chats via MCP with fallback and session memory.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "IRIS - Integrated Runtime Intelligence Service" yet — see the docs or source repo.
Help me design a routing policy for IRIS: use a low-cost model for standard Q&A, switch to a high-performance model for complex reasoning, automatically fall back when the primary model times out or fails, and explain the routing rules for each request type.
A clear routing plan with priorities, fallback conditions, request classification, and policy details.
I want to use IRIS to preserve context for a team assistant. Provide a persistent session design covering session IDs, context storage, history trimming, and how to keep a consistent experience across multi-turn conversations.
A session management recommendation explaining how to save, restore, and optimize multi-turn conversation context.
Based on historical invocation performance, create a continuous optimization mechanism for IRIS: track latency, success rate, cost, and answer quality for each model, then dynamically adjust routing decisions using those metrics.
A performance learning and optimization plan with monitoring metrics, evaluation logic, and dynamic tuning methods.
Search the web, run code, and continue AI-assisted workflows seamlessly.
Lets AI read latest sensor data from MQTT and Sparkplug B streams.
Route LLM requests across providers and orchestrate MCP tools with local privacy.
Access multiple AI providers in one terminal for generation, search, and comparison.
Register multiple AI endpoints and auto-route models by capability.
Aggregate MCP servers and route tools intelligently for efficient parallel work.