Cole-Cant-Code/mantic-thinking: Cross-domain anomaly and opportunity detection using deterministic 4-layer hierarchical analysis. Detects hidden risks before they cascade and optimal windows before they close.

# Friction tool (detect risk)
from tools.friction.healthcare_phenotype_genotype import detect as detect_friction
result = detect_friction(phenotypic=0.3, genomic=0.9, environmental=0.4, psychosocial=0.8)
print(f"Alert: {result['alert']}")  # Warning about mismatch

# Emergence tool (detect opportunity)
from tools.emergence.healthcare_precision_therapeutic import detect as detect_emergence
result = detect_emergence(genomic_predisposition=0.85, environmental_readiness=0.82,
                          phenotypic_timing=0.88, psychosocial_engagement=0.90)
print(f"Window: {result['window_detected']}")  # True - optimal timing

from adapters.kimi_adapter import get_kimi_tools, execute, compare_friction_emergence

# Get all 14 tools
tools = get_kimi_tools()

# Compare friction vs emergence for same domain
comparison = compare_friction_emergence(
    "healthcare",
    friction_params={"phenotypic": 0.3, "genomic": 0.9, "environmental": 0.4, "psychosocial": 0.8},
    emergence_params={"genomic_predisposition": 0.85, "environmental_readiness": 0.82,
                     "phenotypic_timing": 0.88, "psychosocial_engagement": 0.90}
)
# High M in friction = risk. High M in emergence = opportunity.

from adapters.claude_adapter import get_claude_tools, execute_tool, format_for_claude

# Get 14 tools in Computer Use format
tools = get_claude_tools()

# Execute and format for Claude
result = execute_tool("finance_confluence_alpha", {
    "technical_setup": 0.85, "macro_tailwind": 0.80,
    "flow_positioning": 0.75, "risk_compression": 0.70
})
print(format_for_claude(result, "finance_confluence_alpha"))

from adapters.gemini_adapter import get_gemini_tools, execute_tool

# Get tools in Gemini FunctionDeclaration format
tools = get_gemini_tools()

# Or get flat list for simpler SDK usage
from adapters.gemini_adapter import get_gemini_tools_flat
declarations = get_gemini_tools_flat()

result = execute_tool("climate_resilience_multiplier", {
    "atmospheric_benefit": 0.75, "ecological_benefit": 0.80,
    "infrastructure_benefit": 0.78, "policy_alignment": 0.82
})

from adapters.openai_adapter import get_openai_tools, execute_tool
import openai

# Ollama's OpenAI-compatible endpoint
client = openai.OpenAI(
    base_url="http://localhost:11434/v1",
    api_key="ollama"
)

tools = get_openai_tools()
# Works with: minimax-m2.1:cloud, gpt-oss:20b-cloud, glm-4.7:cloud, etc.

from adapters.openai_adapter import get_openai_tools, execute_tool, get_tools_by_type

# Get all 14 tools
tools = get_openai_tools()

# Or filter by type
friction = get_tools_by_type("friction")   # 7 tools
emergence = get_tools_by_type("emergence") # 7 tools

result = execute_tool("cyber_adversary_overreach", {
    "threat_intel_stretch": 0.90, "geopolitical_pressure": 0.85,
    "operational_hardening": 0.80, "tool_reuse_fatigue": 0.88
})