GT AI OS Community v2.0.33 - Add NVIDIA NIM and Nemotron agents

- Updated python_coding_microproject.csv to use NVIDIA NIM Kimi K2
- Updated kali_linux_shell_simulator.csv to use NVIDIA NIM Kimi K2
  - Made more general-purpose (flexible targets, expanded tools)
- Added nemotron-mini-agent.csv for fast local inference via Ollama
- Added nemotron-agent.csv for advanced reasoning via Ollama
- Added wiki page: Projects for NVIDIA NIMs and Nemotron

scripts/migrations/019_add_embedding_usage.sql

@@ -0,0 +1,17 @@
+-- Migration 019: Add embedding usage tracking table
+-- Supports #241 (Embedding Model Pricing)
+
+CREATE TABLE IF NOT EXISTS public.embedding_usage_logs (
+    id SERIAL PRIMARY KEY,
+    tenant_id VARCHAR(100) NOT NULL,
+    user_id VARCHAR(100) NOT NULL,
+    tokens_used INTEGER NOT NULL,
+    embedding_count INTEGER NOT NULL,
+    model VARCHAR(100) DEFAULT 'BAAI/bge-m3',
+    cost_cents DECIMAL(10,4) NOT NULL,
+    request_id VARCHAR(100),
+    timestamp TIMESTAMP DEFAULT NOW()
+);
+
+CREATE INDEX IF NOT EXISTS idx_embedding_usage_tenant_timestamp
+ON public.embedding_usage_logs(tenant_id, timestamp);