See every agent action at the execution boundary

See what your agents tried to do, what scope they asserted, what data they touched, and where governance concerns surfaced.

No API. No account creation. No network calls. Runs entirely locally on your system.

$ pipx install sentience-governor

AI agent governance and execution tracing for modern applications

Get Started

From install to insight in minutes

Sentience is a local-first runtime for observing AI agent execution. It captures structured events (intent, scope, context, and memory access) at the moment actions occur, allowing teams to trace how agents interact with systems without requiring API calls, accounts, or external services.

pipx install sentience-governor
attach to your agent (MCP / LangChain / Claude Code)
run your workflow
inspect the trace

On your first run, you'll see

Missing intent declarationsScope mismatchesUnclassified context exchangesMemory writes worth reviewing

Use in

AI coding assistants
Support agents
Internal automation
Research agents
Evaluating governance for production agents?Talk to us →

The Problem

The gap between model output and real-world action

Model-layer safety

Governs what the model says

  • Prompt filters
  • Content checks
  • Refusal training

Agents don't just respond. They read systems, call tools, write data, and trigger workflows.

Sentience

Governs what the agent does

  • Intent
  • Scope
  • Context
  • Memory
  • Execution boundary

Not a prompt filter. Not a firewall. The governance layer between the model and the world.

Application logging

Captures what happened after

  • Tool logs
  • API traces
  • System logs

Teams see what happened. Not what the agent believed it was doing.

How It Works

Five control points. One structured trace.

Sentience captures governance events at the moments that matter most in agent execution.

01

Agent registration

Who the agent is, what version is running, and what it declares about itself.

02

Intent declaration

What the agent says it is trying to accomplish before it acts.

03

Scope assertion

What the agent is about to read, call, or write.

04

Context snapshot

What data moved through the action, with classifications when available.

05

Memory write attempt

When the agent tries to persist something beyond the current session.

See the Output

$ sentience-cli render ./trace.ndjson

[1] REGISTRATION      Agent claude-langchain-demo-v1
[2] INTENT            Objective: 'Look up customer…'
[3] SCOPE             READ crm_get_customer
[4] CONTEXT           classifications=[]
    POL-003
[5] SCOPE             READ crm_fetch_usage
[6] CONTEXT           classifications=[]
    POL-003
Policy satisfied Advisory surfaced — review recommended

First-run traces often include warnings. That is expected. Sentience makes the gap between intended behavior and actual execution visible.

Integrate in Minutes

Works with how teams build agents today

Four integration paths. No agent rewrites.

Select your integration

For Python agents already using MCP in production.

from sentience_governor.wrapper.mcp import wrap_mcp_client

client = wrap_mcp_client(client, agent_id="your-agent-id")

Coming soon:

MCP registry · Skills distribution · Cursor · Codex · OpenCode

Trust

No data leaves. No payloads inspected. No external dependencies.

No data leaves your system

Sentience is a local Python package. It makes no API calls, requires no account, and connects to no external service by default.

Sync is opt-in only. When enabled, it sends aggregated signals — never raw trace content.

Scope is narrow by design

Sentience reads declared intent, scope, and context metadata at the execution boundary. It does not inspect raw payload content.

Payload classification is only possible when you explicitly provide classification hooks. Nothing is inferred from content.

Auditable by design

Governance events are chained in sequence. A gap, reorder, or missing step is detectable — the trace is structured for audit, not just logging.

Apache 2.0. No vendor lock-in. The runtime is yours to inspect, fork, and run.

Start Local. Scale to Control.

How teams adopt Sentience

Developer → Operator → Enterprise

Open runtime — free, local-onlyControl Plane — enterprise, policy + enforcement

Developer

Free
  • pipx install sentience-governor
  • Local trace
  • Five control points
  • CLI viewer
  • Apache 2.0
Install now →

Operator

Early access
  • sentience-sync
  • Fleet visibility
  • Usage tracking
  • Governance posture
Request early access →

Enterprise

Contact us
  • Policy engine
  • Enforcement modes
  • Audit export
  • SSO + RBAC
Talk to us →

Open runtime is free. Control Plane and enforcement are enterprise.

Sentience

Governance for AI agents at the execution boundary

© 2026 Crescere Labs, Inc. All rights reserved.