Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.brane.membranelabs.org/llms.txt

Use this file to discover all available pages before exploring further.

The coordinator for capabilities and policies. Create one per agent process.

​
Definition

A Runtime owns the capability registry, the policy engine, and the interception machinery. You create one per agent process, configure it with capabilities and policies, and let it govern all capability calls.

​
Constructor

from brane import Runtime

runtime = Runtime(
    agent_id="support-agent",
    environment="prod",
    tenant_id="tenant_acme",
    principal_id="user_sarah",
)
All constructor arguments are optional.
ArgumentTypeDescription
agent_id`strNone`Identity of this agent. Used in every AgentAction record.
environment`strNone`Runtime environment: dev, staging, prod.
tenant_id`strNone`Default tenant for all actions. Can be overridden per action.
principal_id`strNone`Default principal for all actions.
capabilitieslist[Capability]Pre-register capabilities at construction.
policieslist[Policy]Pre-register policies at construction.

​
Owned Components

AttributeTypePurpose
capabilitiesCapabilityRegistryStores and retrieves registered capabilities.
policyPolicyRegistryStores registered policy functions.
policiesPolicyEngineEvaluates actions against registered policies.
interceptorCapabilityInterceptorCore intercept-evaluate-execute loop.
callablesCallableCapabilityInterceptorWraps Python callables with interception and argument binding.

​
Methods

runtime.register_capability(capability: Capability)
Register a capability in the capability registry. 
runtime.capability(name, type, risk, **kwargs)
Decorator that registers the function as a governed capability and wraps it with policy enforcement. 
runtime.wrap_capability(fn, name, type, risk, **kwargs)
Wrap an existing function as a governed capability without decorator syntax. 
runtime.before_capability(target, name=None, version=None)
runtime.after_capability(target, name=None, version=None)
Register policies that run before or after a capability executes. 
runtime.create_action(capability_name, input, action_type=None)
runtime.evaluate_action(action)
runtime.evaluate(capability_name, input)
Create and evaluate actions manually.

​
Common Setups

Minimal local development: 
runtime = Runtime(agent_id="my-agent")
Full production context: 
runtime = Runtime(
    agent_id="support-agent",
    environment="prod",
    tenant_id=request.tenant_id,
    principal_id=request.user_id,
)
Pre-registering capabilities and policies: 
from brane import Capability, Policy, Decision, Runtime

cap = Capability(name="send_email", type="tool", risk="medium")

def block_external_domains(ctx):
    to = ctx.arg("to", "")
    if not to.endswith("@acme.com"):
        return Decision(type="deny", reason="External email addresses are blocked")
    return Decision(type="allow")

policy = Policy(
    target="send_email",
    stage="before_capability",
    function=block_external_domains,
    name="block_external_email",
)

runtime = Runtime(
    agent_id="comms-agent",
    capabilities=[cap],
    policies=[policy],
)
Per-request runtime for multi-tenant systems: 
def handle_request(request):
    runtime = Runtime(
        agent_id="support-agent",
        environment="prod",
        tenant_id=request.tenant_id,
        principal_id=request.user_id,
    )

    runtime.register_capability(SHARED_REFUND_CAP)
    runtime.before_capability("refund_customer")(refund_policy)
One runtime per agent process is the recommended pattern. If you need different tenant or principal contexts per request, create a new Runtime per request with the appropriate identity fields, or override them per create_action call.

​
Future Constructor Arguments

  • audit: AuditSink for recording action events
  • approvals: ApprovalProvider for handling approval_required decisions
  • cloud: CloudClient for remote policy evaluation
  • grants: GrantRegistry for agent capability grants
  • fail_mode: fail-open or fail-closed on policy engine errors