Metadata-Version: 2.4
Name: agentmesh_control_plane
Version: 3.3.0
Summary: Layer 3: The Framework - A deterministic kernel for zero-violation governance in agentic AI systems with POSIX-style signals, VFS, and kernel/user space separation
Home-page: https://github.com/microsoft/agent-governance-toolkit
Author: Microsoft Corporation
Author-email: Microsoft Corporation <agentgovtoolkit@microsoft.com>
Maintainer-email: Microsoft Corporation <agentgovtoolkit@microsoft.com>
License: MIT
Project-URL: Homepage, https://github.com/microsoft/agent-governance-toolkit
Project-URL: Documentation, https://github.com/microsoft/agent-governance-toolkit/tree/main/docs
Project-URL: Repository, https://github.com/microsoft/agent-governance-toolkit
Project-URL: Bug Tracker, https://github.com/microsoft/agent-governance-toolkit/issues
Keywords: ai,agents,governance,control-plane,safety,policy,framework,agentic-ai,llm,guardrails,deterministic,kernel,signals,vfs,syscall
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Security
Classifier: Topic :: System :: Systems Administration
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Typing :: Typed
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: dev
Requires-Dist: pytest<8.0,>=7.0.0; extra == "dev"
Requires-Dist: pytest-cov<5.0,>=4.0.0; extra == "dev"
Requires-Dist: black<26.0,>=25.1.0; extra == "dev"
Requires-Dist: flake8<7.0,>=6.0.0; extra == "dev"
Requires-Dist: mypy<2.0,>=1.0.0; extra == "dev"
Requires-Dist: pre-commit<4.0,>=3.0.0; extra == "dev"
Provides-Extra: sql
Requires-Dist: sqlglot<24.0,>=23.0.0; extra == "sql"
Provides-Extra: hf
Requires-Dist: huggingface_hub<1.0,>=0.20.0; extra == "hf"
Requires-Dist: datasets<3.0,>=2.14.0; extra == "hf"
Provides-Extra: protocols
Provides-Extra: full
Dynamic: author
Dynamic: home-page
Dynamic: license-file
Dynamic: requires-python

# Agent Control Plane — Public Preview

> **Part of [Agent OS](https://github.com/microsoft/agent-governance-toolkit)** - Kernel-level governance for AI agents

[![PyPI version](https://img.shields.io/pypi/v/agent-control-plane.svg)](https://pypi.org/project/agent-control-plane/)
[![Python Version](https://img.shields.io/badge/python-3.8%2B-blue.svg)](https://www.python.org/downloads/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

**Policy-based governance for autonomous AI agents.**

The Agent Control Plane provides a governance layer that sits between your AI agent and the actions it performs. Define policies in YAML or Python and the control plane enforces them deterministically before any action executes.

## Installation

```bash
pip install agentmesh-control-plane
```

## Quick Start

```python
from agent_control_plane import AgentControlPlane

plane = AgentControlPlane()
plane.load_policy("policies.yaml")

result = await plane.execute(
    action="database_query",
    params={"query": "SELECT * FROM users"},
    agent_id="analyst-001"
)
# Safe queries execute; destructive queries are blocked by policy
```

## Features

- Deterministic policy enforcement (YAML or Python)
- Permission management and resource quotas
- Sandboxed execution with rollback support
- Audit logging via SQLite-based Flight Recorder
- Multi-framework support (OpenAI, LangChain, MCP, A2A)

## Documentation

See [docs/](./docs/) for guides and [CONTRIBUTING.md](./CONTRIBUTING.md) for development setup.

## License

MIT License - see [LICENSE](LICENSE) for details.
