TEQUMSA Inference Node

Autonomous multi-agent inference routing and execution for the TEQUMSA Symbiotic Orchestrator.

Features

• Multi-Provider Routing: Intelligent routing to Claude, GPT, Gemini, and Perplexity
• Multiple Execution Modes: Standard, Recursive, Causal, and RDOD execution
• Gradio Interface: Interactive web UI for inference and routing analysis
• Cost & Latency Estimation: Provider cost and latency estimates for routing decisions

Files

• app.py - Gradio inference interface
• inference_router.py - Model routing logic
• tequmsa_space_kernel.py - Core inference engine
• requirements.txt - Python dependencies

Usage

1. Enter a prompt in the Inference tab
2. Select a model provider (or use auto-routing)
3. Choose an execution mode
4. Click "Process Request" to execute

License

OpenRAIL