Skip to main content
Sakshi (साक्षी, “witness”) is a governance layer that sits beside the AI agents you already run. It does not replace your models or your orchestration. It makes them accountable: every agent is inventoried, every decision is recorded on a chain anyone can recompute, autonomy is bounded by policy, and the result is evidence you can hand to an auditor or a regulator. It is built for regulated Indian enterprises first, with clause maps for RBI Model Risk Management, DPDP, SEBI, and IRDAI, and it runs single-tenant inside your own environment.

​
The mental model

As models become agents, the unit of governance shifts from the model to the decision. Sakshi is organized around that idea:

Register

Know Your Agent. A live inventory of every agent and model with an owner, an autonomy tier, provenance, and a verifiable identity. Nothing runs unregistered.

Witness

The flight recorder. Every decision is hashed onto a tamper-evident chain with the model identity, tokenized inputs, and outcome, recomputable by anyone.

Bound

Autonomy envelopes. Each action routes to auto, human review, or block by stakes and confidence, with oversight telemetry and a drilled kill switch.

Vidhi & Vishwas

Evidence and fairness. Regulator instruments encoded as data and scored against live evidence, plus declared-first fairness screens gated on statistical significance.

​
How you connect

There are three ways in, and every one lands on the same chain. Sakshi never sees a raw identifier.

SDK

Wrap your calls in a few lines with the Python SDK.

Middlewares

Add one line to an OpenAI, Anthropic, Gemini, Bedrock, LangChain, LangGraph, Google ADK, CrewAI, or AWS Strands agent.

MCP

Govern any agent that speaks the Model Context Protocol.

Quickstart

Install the SDK, register an agent, witness a decision, and recompute the chain in a few minutes.

Core concepts

The ideas underneath Sakshi: the chain, autonomy envelopes, evidence packs, and PII tokenization.

API reference

Every endpoint, generated from the live OpenAPI spec.

Try a sandbox

A private, synthetic-data instance to poke at, no install required.
Sakshi is single-tenant and runs in your environment, so the base URL in these docs is your own deployment. Examples use the public demo (https://demo.rotavision.com) where a running instance helps.