antarraksha-semantic-kernel 0.1.3

Antarraksha AI Agent Enforcement SDK for Semantic Kernel

antarraksha-semantic-kernel

Antarraksha AI Agent Enforcement SDK for Microsoft Semantic Kernel.

Installation

pip install antarraksha-semantic-kernel

Quick Start

Attach Antarraksha as a prompt filter and function filter on your Semantic Kernel instance. Registration happens automatically on first use — no login, no API key, no signup required.

from semantic_kernel import Kernel
from antarraksha_semantic_kernel import (
    AntarrakshaPromptFilter,
    AntarrakshaFunctionFilter,
)

prompt_filter = AntarrakshaPromptFilter(agent_id="my-sk-agent")
function_filter = AntarrakshaFunctionFilter(agent_id="my-sk-agent")

kernel = Kernel()
kernel.add_filter("prompt_rendering", prompt_filter.on_prompt_render)
kernel.add_filter("function_invocation", function_filter.on_function_invocation)

Run your kernel normally — every prompt render and function invocation is now enforced against Antarraksha policy. DENY raises PermissionError.

Parameters

Parameter	Default	Description
agent_id	None	Unique identifier for your agent. Triggers auto-registration on first use.
base_url	"https://antarraksha.ai"	Antarraksha endpoint. Override for self-hosted / dev.
passport_id	None	Optional pre-issued passport ID (e.g. ANTK-PASS-xxx).
sdk_key	None	Optional pre-issued SDK key. If omitted and agent_id is set, the SDK auto-registers and obtains one.
fail_closed	True	If True, deny on enforcement-server unreachable. Set False for fail-open during early integration.

Corporate Network Note

If you're behind a corporate TLS-inspection proxy and see SSLCertVerificationError, install:

pip install pip-system-certs

This makes Python trust your Windows / macOS system certificate store.