Skip to main content

A lean governance system for AI agents.

Reason this release was yanked:

duplicate

Project description

Agent Governance Cerone Python SDK (Beta)

A lean governance system for AI agents. Cryptographic identity and run-time validation for AI agents in production.

AI agents are being deployed into production systems that handle real decisions, real data, and real consequences, yet most teams have no runtime control over what those agents actually do. Agent Governance fixes that.

Agent Governance enforces cryptographic identity, semantic intent validation, and continuous trust scoring on every agent action; ensuring agents only do what they were authorized to do, and nothing else. Deploying AI agents in production without this layer of protection is an unacceptable operational and security risk.

The SDK is currently in early-access beta for selected teams building production AI systems that require accountability, auditability, and control.

Install

pip install agent-governance-cerone

Access (Beta)

API access is currently managed through early access:

Quick Start

from agent_governance import AgentGovernanceClient
import os

client = AgentGovernanceClient(api_key=os.getenv("AGENT_GOVERNANCE_API_KEY"))

# Create agent
agent = client.create_agent(
    purpose="Email classifier",
    capabilities=["read_email", "move_email", "send_reply"]
)

# Validate action before executing
response = client.validate(
    agent_id=agent.agent_id,
    action="move_email",
    parameters={"email_id": "123", "folder": "spam"}
)

if response.result.value == "approved":
    mailbox.move_email("123", "spam")
else:
    print(f"Action rejected: {response.violations}")

What the SDK Provides

  • Authenticated client access to Agent Governance services
  • Agent registration and identity-bound operations
  • Sync and async validation calls
  • Batch validation support
  • Governance-oriented telemetry surfaces

Compatibility

The PyPI package name is agent-governance-cerone. Existing cerone imports continue to work in this release. New integrations should use:

from agent_governance import AgentGovernanceClient

Usage Terms

Usage limits and commercial terms are defined in TERMS_OF_SERVICE.md.

Current free trial: up to 25 validations in the first 5 days.

License

Proprietary commercial license. See LICENSE.

Contact

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agent_governance_cerone-1.1.1-py3-none-any.whl (13.4 kB view details)

Uploaded Python 3

File details

Details for the file agent_governance_cerone-1.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for agent_governance_cerone-1.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 b603b07daf0ed45fa5a6df2fcf16f91a8d727d3c0e7fde2c97b1cbbf855548d2
MD5 a0c1843921ee9937a0e515b563f83c13
BLAKE2b-256 99cf10ee287f85dc1206aeef3f91c206c879bbf6decf2d16f3662b446bca5177

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page