Frequently asked questions

Sentience Governor records agent execution and evaluates actions against declared scope and applicable runtime policies. It retains the agent's declared objective as execution context, providing evidence of what the agent intended and what it actually did. Before acting, an agent declares an objective and the scope it needs. Governor captures structured events at the execution boundary (registration, intent, scope, context, memory writes) and evaluates each action as it happens.

Traditional logs and observability primarily record what happened. Sentience Governor also captures the agent's declared intent, asserted scope and runtime context, then evaluates actions against the declared scope and applicable runtime policies during execution. The result is a structured record that humans and policy systems can reason about, rather than a stream of events to search through afterwards.

No. Sentience Governor runs entirely locally as a Python package. It does not require an API, account creation, or an external service. By default nothing leaves your machine. An operator can configure a sink to send events somewhere else, but that only happens if you set it up.

Sentience Governor reads the agent's declared intent and scope, and for each action the tool name, target system, operation type and classification metadata. It does not inspect raw payload content unless the integrator explicitly provides a classification hook.

Not by default. Sentience Governor is advisory and non-blocking by default: it records and evaluates, and does not block, pause or modify agent actions. When an action falls outside the declared scope, it raises a policy violation in the trace and the action still proceeds. To act on those findings at runtime, Sentience Runtime Enforcement adds course correction, human escalation or stopping execution through control points integrated with your existing infrastructure. It does not require Secure Runtime.

Five control points produce structured governance events: agent registration, intent declaration, scope assertion, context snapshot and memory write attempt. Events also carry execution telemetry for the turn they belong to: token counts, model and provider. That lets teams associate compute spend with the turn and action context where it occurred, rather than only with a session total.

Policy is an operator-authored YAML profile. It controls when intent must be declared, which task-boundary signals are active (directory change, file-type shift, time gap, read-to-write transition), and which tool patterns count as high-consequence. Today each machine uses one configured profile. It is bound into each session and its fingerprint is recorded with the resulting evidence, so Sentience Governor can show which policy applied to which run. Every match currently produces a flag. Scoping policy per team or environment, and acting differently by risk tier, is the enterprise direction.

An append-only JSONL trace of governance events. Each event is sequence-chained to the one before it, so gaps and reordering are detectable. Policy violations and advisory flags are reported separately from one another, and the sentience CLI renders a session view for quick inspection.

Sentience Governor integrates with existing agent setups without requiring rewrites: Claude Code hooks and slash commands, a dedicated Pydantic AI integration package, an MCP client wrapper, an opt-in MCP server, a LangChain callback handler and LangGraph middleware.

No. They answer different questions. Model safety governs model inputs and outputs. Observability records execution. Sentience Governor evaluates runtime actions against the governance context declared for the session.

Developers who want to understand agent behaviour, operators who need visibility across systems, and enterprises preparing for governance and enforcement.

Sentience Governor is one of three Sentience products. Runtime Governance (Sentience Governor, free and open source) is advisory: it evaluates each action against the declared scope and policy and records the evidence. Runtime Enforcement acts on those evaluations through control points integrated with your existing infrastructure, and includes Runtime Governance. Secure Runtime runs agents in isolated execution environments with governance and enforcement integrated. Runtime Enforcement does not require Secure Runtime.