Quickstart

This walks through the shortest path to an accountable agent: register it, witness one decision, and verify the record independently. It takes a few minutes.

Prerequisites

Python 3.9 or newer
A writable Sakshi instance you can reach: your own deployment, or a sandbox, a private synthetic-data instance with no install. The public demo at https://demo.rotavision.com is read-only, so it cannot register or witness.
An ingest API key. In a sandbox or your own deployment, mint one in the console under Admin → API keys. See Authentication.

1. Install the SDK

pip install sakshi-sdk

The distribution is sakshi-sdk; the import is sakshi.

2. Initialize the client

from sakshi import SakshiClient

client = SakshiClient(
    base_url="https://sakshi.your-company.internal",
    api_key="sks_...",
)

Capture is fail-open by default: if the platform is unreachable, your agent keeps running and records are dropped with a warning. Governance must never take production down. Pass fail_open=False for batch jobs where losing evidence is worse than stopping.

3. Register the agent

An agent must not run unregistered. register is idempotent by name, so it is safe to call on every startup.

agent_id = client.register(
    "loan-decision-agent",
    owner_name="Priya Sharma",
    owner_email="priya@your-company.com",
    autonomy_tier="L1",
    description="Approves or refers retail loan applications.",
)

4. Witness a decision

Open a witness session as a context manager. Record the steps as they happen; the decision record is written to the chain when the block exits. Identifiers you pass are tokenized at ingest, so raw PII never lands on the chain.

with client.witness(
    agent_id,
    model={"provider": "openai", "name": "gpt-5.2", "version": "2026-05"},
    context={"applicant_aadhaar": "XXXX-XXXX-1234"},
    client_ref="APP-2026-04471",
) as decision:
    decision.step("retrieve", source="credit-bureau")
    decision.step("assess", risk_band="low", score=0.92)
    decision.action(outcome="approved", amount=1_500_000, mode="auto")

5. Bound the autonomy (optional)

Before an agent acts, route the intended action through its envelope. Enforcement fails closed: if Sakshi is unreachable it raises rather than letting an ungoverned action through.

from sakshi import SakshiBlocked, SakshiSyncReviewRequired

try:
    client.enforce(agent_id, "approve_loan", stakes=1_500_000, confidence=0.92)
    # allowed: proceed with the action
except SakshiSyncReviewRequired:
    # parked for a human before it can run
    ...
except SakshiBlocked:
    # the envelope (or the kill switch) blocked it
    ...

6. Verify the chain

Anyone can recompute the chain. No trust in Rotavision required.

curl -H "Authorization: Bearer sks_..." \
  https://sakshi.your-company.internal/api/v1/chain/verify

{ "valid": true, "checked": 1842, "first_invalid_seq": null }

Tamper with a single field in any record and valid becomes false, and the chain says exactly where it broke.

Next steps

Add it with one line

Wrap an existing OpenAI, Anthropic, LangGraph, Google ADK, CrewAI, or AWS Strands agent with a middleware instead of hand-instrumenting.

Bound autonomy

Publish an autonomy envelope, arm circuit breakers, and drill the kill switch.

Generate an evidence pack

Map your live records to RBI, DPDP, SEBI, or IRDAI obligations and export a signed bundle.

Full SDK reference

Every client method, the witness session, and the exception model.

Getting Started

Core Concepts

Predict & Prevent

Guides

Prerequisites

1. Install the SDK

2. Initialize the client

3. Register the agent

4. Witness a decision

5. Bound the autonomy (optional)

6. Verify the chain

Next steps

Add it with one line

Bound autonomy

Generate an evidence pack

Full SDK reference

​Prerequisites

​1. Install the SDK

​2. Initialize the client

​3. Register the agent

​4. Witness a decision

​5. Bound the autonomy (optional)

​6. Verify the chain

​Next steps

Add it with one line

Bound autonomy

Generate an evidence pack

Full SDK reference

Prerequisites

1. Install the SDK

2. Initialize the client

3. Register the agent

4. Witness a decision

5. Bound the autonomy (optional)

6. Verify the chain

Next steps