KAVACHKAVACH
v2.0.1

Overview

KAVACH is an open governance and control plane for AI agents, workflows and decisions. It provides evaluation, policy enforcement, execution control, auditability and deterministic governance across REST APIs and MCP tools.

What is KAVACH

Kavach is a governance control plane for AI systems. It records governed AI assets, evaluates AI configurations, persists execution evidence, reconstructs history, analyzes quality change, ranks experiment candidates, and produces recommendations. It does not own prompt deployment, model deployment, infrastructure orchestration, or CI/CD execution.

Kavach sits between the systems that run AI work and the organization that must account for it. It records what happened, evaluates it against explicit policy, produces a deterministic decision with supporting evidence, and stores an immutable trail for replay and investigation.

Architectural Planes

The system is organized into independent planes. Each plane owns a single responsibility and communicates only through explicit contracts:

  • Audit Plane — captures workflow and node-level execution records for reconstruction and investigation.
  • Replay Plane — reconstructs historical executions from persisted audit state.
  • Evaluation Plane — turns workflow outputs into evaluation results using pluggable providers.
  • Job Execution Plane — records and executes long-running governance work with durable lifecycle tracking.
  • Persistence Plane — stores governed artifacts through replaceable repository contracts.
  • History Plane — retrieves and organizes evaluations into history views, trends, and comparisons.
  • Governance Plane — analyzes change over time, calculates drift, and produces governance-oriented artifacts.
  • Governance Ontology Plane — semantic graph describing relationships between governed assets.
  • Settings Control Plane — typed configuration with SYSTEM, ORGANIZATION and PROJECT scopes.

See the architecture overview for a full breakdown of each plane and how they interact.

Interfaces

Every governance operation is available over a versioned REST API and as an auditable MCP tool. The MCP server exposes governed read and controlled-write operations to agents, while the REST APIs serve consoles, CLIs and service-to-service integrations.

Where to start