Get Started

From zero to governed
in under 15 minutes.

Install Nomotic, register your first agent, apply your first governance policy, and generate your API key. Everything you need to put a behavioral control plane on your agents today.

pip install nomotic
Full Documentation →
01

Install Nomotic

A single pip install with zero required dependencies.

⏱ ~2 min
🐍

Python 3.9+

Check your version with python --version

Download Python →
📦

pip 21+

Upgrade with pip install --upgrade pip

🌐

Internet access

For initial install only. Runtime has zero external calls.

terminal
pip install nomotic

Verify the installation:

terminal
nomotic --version
nomotic 0.7.0
Behavioral Control Plane™ — ready
Virtual environment recommended. Create one with python -m venv .venv && source .venv/bin/activate before installing. This keeps your Nomotic install isolated from other projects.

02

Register Your First Agent

Every governed agent starts with a birth certificate — a cryptographic identity bound to a governance policy.

⏱ ~3 min

Connect Nomotic to your agent and give it an identity. Nomotic supports any agent framework — LangGraph, CrewAI, AutoGen, or custom Python.

register_agent.py
from nomotic import Nomotic, AgentConfig

# Initialize the Behavioral Control Plane™
nomotic = Nomotic.init(
    api_key="nom_your_api_key_here", # from Step 4
    environment="development"
)

# Register your agent with a birth certificate
agent = nomotic.register_agent(
    AgentConfig(
        name="my-first-agent",
        archetype="general", # or healthcare, finance, etc.
        description="My first governed agent",
        owner="your-team",
    )
)

print(f"Agent registered: {agent.certificate_id}")
Agent registered
  Certificate: NOM-8C4F2A1E
  Archetype: general
  Trust score: 0.500 (baseline)
  Status: ACTIVE
Your agent now has an identity. The certificate ID is unique, cryptographically signed, and bound to your governance policy. Every action this agent takes will carry this identity.

Available archetypes — pre-built governance configurations for common use cases:

ArchetypeUse CaseKey Constraints
generalGeneral purpose agentsBalanced defaults across all 14 dimensions
healthcareClinical, patient dataHIPAA-aligned, strict data isolation
financeTrading, risk, complianceJurisdictional veto, audit requirements
customer-serviceCustomer-facing agentsStakeholder impact, tone enforcement
data-pipelineETL, data processingScope compliance, resource limits
code-executionCode generation/execIsolation integrity, scope veto

03

Apply a Governance Policy

Define what your agent is allowed to do — and what it absolutely cannot.

⏱ ~5 min

A governance policy defines the 14-dimensional evaluation parameters for your agent. Start with a simple policy and extend it as your needs grow.

governance_policy.py
from nomotic import GovernancePolicy, VetoRule, Dimension

policy = GovernancePolicy(
    name="my-first-policy",

    # Hard veto rules — absolute, no weighting overrides these
    veto_rules=[
        VetoRule.SCOPE_VIOLATION, # agent must stay in scope
        VetoRule.ISOLATION_BREACH, # no cross-tenant data access
        VetoRule.ETHICAL_VIOLATION, # ethical constraint is absolute
    ],

    # Weighted dimensions — scored 0.0 to 1.0
    dimensions={
        Dimension.BEHAVIORAL_CONSISTENCY: 0.8, # threshold
        Dimension.STAKEHOLDER_IMPACT: 0.7,
        Dimension.HUMAN_OVERSIGHT: 0.6,
        Dimension.TRANSPARENCY: 0.75,
    },

    # Minimum Unified Confidence Score to proceed
    ucs_threshold=0.70,

    # Escalate to human when Value of Information exceeds cost of delay
    voi_escalation=True,
    voi_threshold=0.85,
)

# Apply to your registered agent
agent.apply_policy(policy)
print(f"Policy applied: {policy.policy_id}")
Policy compiled and applied
  Policy ID: POL-2F8A19C4
  Veto rules: 3 active
  Weighted dimensions: 4 configured
  UCS threshold: 0.70
  VOI escalation: enabled at 0.85

The 14 governance dimensions evaluated on every action:

DimensionTypeWhat it governs
Scope ComplianceVetoAgent stays within defined operational boundaries
Isolation IntegrityVetoNo unauthorized cross-context data access
Ethical ComplianceVetoHard ethical constraint enforcement
Jurisdictional ComplianceVetoRegulatory and geographic constraints
Behavioral ConsistencyWeightedActions align with established behavior patterns
Stakeholder ImpactWeightedDownstream effect on affected parties
Human OversightWeightedHuman review requirements for sensitive actions
TransparencyWeightedAction explainability and auditability
Resource AuthorizationWeightedBudget and resource limits respected
Temporal ComplianceWeightedTime-bounded and scheduled constraint enforcement
Precedent AlignmentWeightedConsistency with prior approved actions
Incident DetectionWeightedReal-time anomaly and incident identification
Authority VerificationRequiredAgent identity and permission confirmation
Trust ScoreRequiredCumulative behavioral trust history

04

Generate Your API Key

Authenticate your runtime connection to the Nomotic Behavioral Control Plane™.

⏱ ~1 min

API keys authenticate your agents to the Nomotic runtime. Each key is scoped to your organization and can be restricted to specific agents, environments, or permission levels.

terminal
nomotic keys create \
  --name "development" \
  --env development \
  --scopes govern,audit,read
Save your key immediately. It is shown once and cannot be retrieved again. Store it in an environment variable or secrets manager — never in source code.
.env
NOMOTIC_API_KEY=nom_sk_your_key_here

API Key — development

ACTIVE
Key ID nom_sk_dev_•••••••••••• Reveal
Name development Rename
Env development
Scopes govern · audit · read
Created just now
Last used Never

05

Run Your First Evaluation

Govern a real action and see the Behavioral Control Plane™ return a verdict.

⏱ ~3 min

Submit an action to the governance runtime and receive a verdict in sub-millisecond time. The verdict includes a full 14-dimensional breakdown and a Unified Confidence Score.

first_evaluation.py
from nomotic import Nomotic
import os

nomotic = Nomotic.init(api_key=os.getenv("NOMOTIC_API_KEY"))
agent = nomotic.agent("my-first-agent")

# Govern any action before it executes
verdict = agent.govern(
    action="read_customer_record",
    target="customer_db",
    context={
        "purpose": "generate_report",
        "requester": "pipeline-job-42",
        "data_sensitivity": "medium",
    }
)

# Check the verdict before proceeding
if verdict.allowed:
    print(f"Proceeding. UCS: {verdict.ucs}")
    # execute your action here
else:
    print(f"Denied: {verdict.reason}")

What the verdict looks like:

ALLOW verdict
VERDICT
ALLOW · UCS 0.847
certificateNOM-8C4F2A1E
latency0.62ms
trust_score0.514
veto_checks3 / 3 PASS
dimensions14 / 14 scored
sealSEAL-F2C...
DENY verdict
VERDICT
DENY · VETO
certificateNOM-8C4F2A1E
latency0.41ms
veto_triggeredSCOPE_VIOLATION
reasontarget out of scope
dimensionsevaluation halted
sealSEAL-91A...
🎉
Your agent is governed. Every action now runs through the Behavioral Control Plane™ before executing. Verdicts are hash-chained to a tamper-evident audit trail automatically.
Stay Governed

The Governance Brief.

Industry analysis, competitive intelligence, and technical deep dives
on governing AI agents. Biweekly.