agent_governance_toolkit
Public Preview — Unified installer and runtime policy enforcement for the Agent Governance Toolkit
Decision gist · record as of 2026-08-14
Yes, if you are building production AI agents and need integrated governance across policy, trust, execution control, and reliability. The unified install eliminates version conflicts and ensures component compatibility. However, the package is in public preview with potential API changes; evaluate your tolerance for breaking changes before general availability. No known security vulnerabilities and low install friction support adoption.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later; package is in public preview with APIs subject to change before general availability.
- Low friction install with three common dependencies (pydantic, pyyaml, click).
- Active maintenance with recent commits; package is in public preview with potential API changes before general availability.
License · maintenance · safety
MIT (permissive) — MIT license permits unrestricted use, modification, and distribution with minimal attribution requirements, suitable for both open-source and commercial projects.
last release 2026-06-11 (64 days) · last repo commit 2026-08-14 · 5,928 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 130,624 downloads/mo, #11,633 on PyPI
Alternatives
Verify before relying
pip install agent-governance-toolkit
from agent_governance_toolkit import GovernanceVerifier
verifier = GovernanceVerifier()
attestation = verifier.verify()
print(f"Grade: {attestation.compliance_grade()}")- Which of the four component layers (kernel, trust mesh, runtime, SRE) are included in base install versus optional extras.
- Specific OWASP compliance controls and regulatory frameworks (GDPR, HIPAA, SOX) actually implemented.
- Performance characteristics and scalability limits for governed agent execution.
- Actual compatibility with LangChain, CrewAI, and AutoGen beyond installation examples.
What it is and what it does
Agent Governance Toolkit is a meta-package that provides a unified installation for governance infrastructure across four layers: a policy engine for deterministic action evaluation, trust infrastructure for agent identity and secure communication, an execution supervisor for resource and context control, and reliability engineering tools for SLO enforcement and incident response. It solves the problem of deploying AI agents to production without governance by bundling version-compatible components that work together out of the box. The package is currently in public preview, meaning APIs may change before general availability, and it is designed to integrate with popular agent frameworks.
Use it for
- Enforce capability-based access control for agents calling external tools or databases in regulated environments.
- Establish zero-trust identity and encrypted communication between multiple agents in a distributed system.
- Prevent runaway agents from consuming unbounded resources through execution rings and resource limits.
- Generate immutable audit trails and compliance attestations for agent decisions in regulated organizations.
- Monitor agent health and automatically trigger incident response when reliability thresholds are breached.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building production AI agents and need integrated governance across policy, trust, execution control, and reliability.
The unified install eliminates version conflicts and ensures component compatibility. However, the package is in public preview with potential API changes; evaluate your tolerance for breaking changes before general availability. No known security vulnerabilities and low install friction support adoption.
Install
agent-governance-toolkit on PyPI
Before you install
Low friction install with three common dependencies (pydantic, pyyaml, click). Active maintenance with recent commits; package is in public preview with potential API changes before general availability.
Requires Python 3.9 or later; package is in public preview with APIs subject to change before general availability.
License in practice
MIT license permits unrestricted use, modification, and distribution with minimal attribution requirements, suitable for both open-source and commercial projects.
Quickstart
pip install agent-governance-toolkit
from agent_governance_toolkit import GovernanceVerifier
verifier = GovernanceVerifier()
attestation = verifier.verify()
print(f"Grade: {attestation.compliance_grade()}")Verify before relying
- Which of the four component layers (kernel, trust mesh, runtime, SRE) are included in base install versus optional extras.
- Specific OWASP compliance controls and regulatory frameworks (GDPR, HIPAA, SOX) actually implemented.
- Performance characteristics and scalability limits for governed agent execution.
- Actual compatibility with LangChain, CrewAI, and AutoGen beyond installation examples.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 3 packagespydanticpyyamlclick |
| Maintenance | Actively maintained 64 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 130,624 / month, #11,633 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.9Topic :: Scientific/Engineering :: Artificial IntelligenceTopic :: SecurityTopic :: Software Development :: Libraries :: Application Frameworks |
Evidence: agent_governance_toolkit-4.1.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “ai agent governance”
- agent_governance_toolkitUnified installer that bundles policy enforcement, agent identity and…
- agent-governance-toolkit-cliProvides CLI tools, SRE observability, and sandbox isolation for…
- agentrust-traceCreates and verifies cryptographically signed Trust Records that…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also agent-governance-toolkit-cli · agent-governance-toolkit-core · agentrust-trace · compliance-trestle · cpex · agent-framework-purview · aigie · nvidia-nat-core · bernstein · bittensor-cli