sakshi-sdk 0.1.0

Sakshi SDK — register AI agents, witness their decisions, enforce their autonomy envelopes

sakshi-sdk

Register your AI agents and witness their decisions. Python SDK for the Sakshi governance platform.

pip install sakshi-sdk   # imports as `sakshi`

from sakshi import SakshiClient

sakshi = SakshiClient("https://console.example.bank", api_key="...")

agent_id = sakshi.register(
    "loan-decision-agent",
    owner_name="Priya Sharma",
    owner_email="[e-mail]",
    autonomy_tier="L2",
    blast_radius={"customer_facing": True, "spend_limit_inr": 500_000},
)

with sakshi.witness(
    agent_id,
    context={"application_id": "4471", "retrieved": chunks},
    model={"provider": "openai", "model": "gpt-5.2", "version": "2026-05"},
    client_ref="app-4471",  # idempotency key
) as w:
    w.step("plan", goal="assess repayment capacity")
    w.tool("bureau_pull", output=bureau_response)
    w.human("async_review", "[e-mail]", verdict="approved")
    w.action(decision="approve", limit_inr=200_000)

Properties you can rely on:

• Fail-open by default — if the platform is unreachable, your agent keeps running; records are buffered, retried, and dropped with a warning as the last resort. Governance must never take production down. Use fail_open=False for synchronous capture that raises.
• Failures are evidence — an exception inside a witness block is captured as the decision outcome and re-raised.
• PII-safe by design — Aadhaar/PAN/mobile and other Indian identifiers are detected and tokenized server-side at ingest, before storage or hashing.
• register() is always synchronous: an unregistered agent should not run (RBI draft MRM guidance, para 21).

Call sakshi.flush() before shutdown in batch jobs; long-running services can rely on the atexit hook.