Skip to main content

Ship AI faster.
Stay in control.
Prove every decision.

DVARA is an AI gateway that governs model, tool, and agent-to-agent calls. Apply policy and PII checks, keep tamper-evident evidence, and control agents that loop.

Book a DemoRun DVARA

Product animation showing the control gaps created when AI applications, agents and coding assistants connect directly to models and tools. DVARA becomes the common enforcement point for identity, policy, PII, budget, approval and loop controls, then records each signed decision.

Customers

Trusted by teams building production AI.​

HealthYoda.aiBarrister24flutrrpersistX
Runs in your infrastructure

Keep governance data under your control.

Deploy DVARA in your VPC, cloud, or on-premises environment. Policies, credentials, budgets, and audit records remain in infrastructure you operate. Requests go only to the providers and tool servers you configure.

  • Deploy in your infrastructureRun DVARA in your VPC, cloud, or on-prem.
  • Use your provider keysStore encrypted credentials in your install or reference your own vault.
  • Verify the audit trailInspect HMAC-signed, hash-chained records for governed calls and decisions.
Three governed paths

One AI Gateway for models, tools and agents.

Model calls pass through the DVARA LLM Gateway, tool calls through the MCP Gateway, and agent handoffs through the A2A Gateway. All three use the same policy and evidence model.

AI apps and agents
One shared platformDVARA
  • Identity
  • Policy
  • Data
  • Spend
  • Evidence

DVARA LLM Gateway

Model callsModels

DVARA MCP Gateway

Tool callsTools

DVARA A2A Gateway

Agent handoffsPeer agents

Why DVARA

Governance is built into the request path.

Enforce policy and protect data

Apply versioned policy and PII controls before calls reach models and tools. PII detection logs by default; select redaction or blocking when enforcement is required.

Explore Policy-as-Code →

Control tools and autonomous agents

The Enterprise platform governs registered MCP tool calls and A2A handoffs with configured policy, data checks, approval rules and loop controls.

Explore tool and agent governance →

Investigate decisions with evidence

HMAC signatures and hash chaining reveal changed, deleted or missing supported governance records during verification.

Explore audit evidence →
See how DVARA compares with other AI gateways →
Flightdeck

Find the decision. Export the evidence.

Filter runtime decisions by workspace, event, and date. Review applicable allow, deny, redaction, and approval decisions, then export the records your security and compliance teams need.

  • Policy decisions
    See ALLOW or DENY, the deciding rule and the reason.
  • Data-protection actions
    See what was detected and the configured action that ran.
  • Human approvals
    For governed MCP calls, inspect the held request and the decision that released or refused it.
  • Signed audit records
    Verify HMAC signatures and hash-chain continuity for LLM governance records.

Use the exported records as evidence for SOC 2, HIPAA, and GDPR reviews. DVARA does not make your organization compliant.

See how reports are generated
DVARA Flightdeck Audit Log with tenant, event type and date filters above an exportable event tableDVARA Flightdeck Audit Log with tenant, event type and date filters above an exportable event table
Filter governed events and export evidence without assembling it from application logs.
FAQ

Questions teams ask before they deploy.

What does DVARA govern?

DVARA governs model calls that pass through the DVARA LLM Gateway. It applies configured identity, policy, data, spend, and evidence controls on the request path. Registered MCP tool calls and agent-to-agent traffic use the DVARA MCP Gateway and A2A Gateway.

See the governance architecture →

Do we need to change our application?

For OpenAI-compatible model calls, you usually change only the base URL and credential. Your existing SDK sends the request to the DVARA LLM Gateway, which returns an OpenAI-compatible response. MCP and A2A traffic use their corresponding DVARA gateway paths.

Run the quickstart →

Where does DVARA run?

The Open Source distribution runs as one self-managed LLM Gateway with file configuration. The Enterprise platform runs with Flightdeck and persistent storage in your VPC, cloud account, or on-premises environment. Dedicated managed hosting is also available through DVARA.

Deployment models compared →

What data leaves our environment?

DVARA sends each model request to the provider you choose and each governed tool call to the MCP server you registered. The Open Source distribution keeps file configuration and optional audit records locally. A self-managed Enterprise deployment stores its managed configuration, credentials, budgets, and audit records in infrastructure you operate.

Review the data boundary →

How is DVARA different from other AI gateways?

Most AI gateways standardise provider APIs and route model traffic. DVARA also governs every call: a tamper-evident audit trail, policy and personal-data checks on every call, and limits that stop agents that loop. Routing and OpenAI compatibility come standard.

Compare DVARA with AI gateways →

Bring one production AI workflow.

See how DVARA would govern its model, tool and agent calls—and what evidence your teams would receive.

Book a DemoRun DVARA