Skip to main content
Announcement: Now accepting design beta partners · Read more

Maya Agentic Firewall

One console for the whole fleet:

The Maya console: the Agents view with 12 of 12 active agents, AI egress at 1.4 MB/hr average, two open deviations, and the agent-to-agent activity graph.

Tap to enlarge

Twelve agents, three zones, one red edge. Every line is attributed to the agent that opened it. Nothing on this board is derived from an IP address.

Maya Policy Control Loop

Network activity

Control layer

Maya

  • Declare
  • Observe
  • Detect
  • Judge
  • Enforce

Agent-level control

  • Identify your agent fleet

    Every agent, and every shadow, becomes visible.

  • Fence your agents

    You define an agent's policy mandate.

  • Gather operational evidence

    Every connection is tied to the agent that made it.

  • Control agent behavior

    Every agent can be judged and acted on precisely.

Step one · Declare

You declare the policy mandate.

Every agent gets stated limits. The same shape as any desk mandate: who, what, where, when, how much.

Who it may talk to

Peers

What it may reach

Providers

Where it may go

Reach

Which way

Direction

When

Window

How long

Lifetime

How often

Rate

How much

Budget

This is the approved-provider list you already maintain, written where it can be measured against.

Step two · Observe

See every agent and its actual relationships.

The mandate defines what should happen. Observation shows what is happening, including activity from agents nobody declared.

  • Agents and context

    Reconcile declared agents with workload, runtime, region and time observed on the network.

  • Potential shadow agents

    Surface undeclared processes reaching models or agent endpoints for investigation, and enroll them into the fabric.

  • Actual relationships

    See the model providers, MCP servers, tools, peer agents and services each agent reaches.

Traffic on a highway. Conventional flow tools see only the lanes; Maya labels each individual vehicle with the agent driving it, and flags one whose declared mandate does not match the provider it reached.
The lane is the workload. The vehicle is the agent. Observe reveals which agent is moving through it.

Step three · Detect

Identify the gap between policy and behavior.

For declared limits, Maya produces a named deviation, timestamped and attributed to one agent.

Declared mandate

Agent
settlement-recon
Approved providers
Anthropic · Azure OpenAI
Approved peers
ledger-svc · fx-quote
Reach
Internal · external

Observed on the wire

Agent
settlement-recon
Provider
Gemini
Peer
ledger-svc
Reach
External

Detected deviation

Deviation type
Provider outside mandate
Agent
settlement-recon
Expected / observed
Anthropic or Azure OpenAI / Gemini
Context
AWS us-east-1 · Tue 09:14:22

Evidence produced

Deviation type · Agent ID · Expected · Observed · Workload · Region · Timestamp

Ready for automation

Export the deviation to SIEM, observability or case-management systems.

Step four · Judge

Judge turns evidence and authority into a decision.

Deterministic rules and contextual evaluation determine the verdict and response policy.

Judgment architecture

Evidence

  • Detected finding
  • Agent mandate
  • Behavior and relationships
  • External intelligence

Decision authority

  • Declared response policy
  • External policy engine
  • Human review

Judge

Intelligence layer

Deterministic

Explicit rules resolve the verdict

Non-deterministic

Evidence and context shape the verdict

Decision

Verdict

Response policy

What should happen next

Example Large outflow aloneDecision: Zoom + malicious-IP matchDecision: stronger response

Step five · Enforce

Enforce the decision on one agent.

Stop, log, export, inspect or redirect at the wire, without disrupting the rest.

Stop

Drop the agent or block selected flows and agent-to-agent conversations.

Log

Record the activity and allow the connection to continue.

Export

Send the finding and evidence to the institution's existing systems.

Zoom

Increase resolution around one agent and return new evidence to Judge.

Redirect

Send selected traffic to a controlled destination or review path.

Enforcement

Acts on an agent's new traffic. Reversible.

1 enforced
AgentActionScopeSince
claims-triage
us-east-1a
blocking Gemini new flows to that provider only 2m ago Revert
disclosure-drafter
us-west-2b
monitoring Enforce
One row changed. Eleven other agents on the same hosts were not touched, and the revert is one click away.*

The action follows the agent, not the host, workload or shared identity. One agent is controlled. The others keep working.

1 of 5

Onboarding

Maya agent detection

Undeclared agent traffic on a Maya host is detected and auto-enrolled onto the fabric. You get a roster before you get a policy.

Agents

Who's running, and what they're doing

1 newly discovered
AgentHostDeclarationTagsSeen
kyc-screening
eu-west-1a 7 of 8 declared compliance=dora now
ledger-core
us-east-1a 8 of 8 declared compliance=sox now
forecast-helper
discovered on the wire · enrolled automatically
us-east-1a no declaration — nothing to govern undeclared 4m
fraud-scoring
us-east-1a 8 of 8 declared data_class=financial now
An agent nobody told Maya about. Enrolled, named and attributed within minutes of its first packet. Visible, and explicitly not governed.

Reference

The deviation catalog

You declare. Maya observes. Every gap between the two is a typed event with a durable ID, not a log line someone has to go find.

TypeYou declareIt fires when
PROVIDERSModel and inference providers this agent may reachIt reaches a provider outside the list
REACHThe destination classes it may touchIt leaves its class. The exfiltration signal
PEERSThe agents it may talk toAn undeclared A2A edge appears
DIRECTIONALITYWhether it initiates, receives, or bothA receive-only agent starts dialing out
EGRESS_BUDGETA byte ceiling per agent75 percent warn, 100 percent critical. Arithmetic, no model in the loop
RATEConnections and bytes per unit timeIt goes loud
TEMPORALThe hours it is expected to workIt runs outside its window
TTL_LIFECYCLEHow long it should liveIt outlives its declared lifetime

Deviations

Declared, then observed. Every gap, typed.

4 open
TypeAgentDetailIDAge
PROVIDERS
claims-triage
us-east-1a
declared anthropic, bedrock — reached openai dv-8c41f0 3m
PEERS
invoice-reconciler
us-east-1a
undeclared edge to statement-gen dv-8c3ea7 21m
EGRESS_BUDGET
disclosure-drafter
us-west-2b
78% of declared ceiling — warn dv-8c39b2 1h 04m
TEMPORAL
treasury-sweep
us-west-2b
ran 02:14 — declared window 06:00 to 20:00 dv-8c2d40 6h 12m
Four types firing at once. Each carries the agent, the declaration it broke, and an ID that survives restarts.

In your stack

Maya decides nothing you would rather decide yourself

SIEM and SOAR

Deviations stream out of the northbound API. Splunk, Sentinel or XSOAR decides, the action step posts the verdict back, Maya installs it in-kernel.*

Observability

Per-agent flow and deviation telemetry exports as OTLP. Agent attribution lands next to the traces your LLM tooling already collects.*

Bring your own judgment

Point the stream at Open Policy Agent, a Cedar policy, or an agent of your own. Your engine returns a decision, Maya actuates it.

Export

Where deviations and per-agent telemetry go

4 live
Datadog
OTLP · per-agent flow and deviation metrics
Grafana
OTLP · per-agent flow and deviation metrics
Splunk
Deviation stream · typed events with durable IDs
Northbound API
Your SIEM or SOAR decides · Maya installs the verdict
Maya is the feed, not the arbiter. The judgment stays wherever you already keep it.

Product spec

Maya Agentic Firewall spec

Form factorMaya appliance instance in your VPC or VCN. Stitch host shim on each agent host.
DatapatheBPF in the Linux kernel, TC/TCX. Geneve overlay between host and the Maya appliance.
Agent declarationMAYA_AGENT_ID in the process environment. No code change, no SDK, no sidecar.
TLSNever terminated. Never decrypted. No certificate to install, no private key to hand over.
Deviation typesEight. See the catalog above.*
EnforcementPer agent, operator controlled, reversible. Acts on new traffic.*
Telemetry outOTLP to your collector. Datadog, Grafana, Splunk.*
Northbound APIDeviation stream out, verdicts in. Driven directly by a SIEM, SOAR or policy engine.*
ConsoleManagement plane. Agent roster, A2A conversation graph, deviation stream, enforcement.
Control planeRegional.
CloudsAWS and GCP.*

Table 2 · Host requirements

Maya currently only supports agents running on a Linux host. See below for detailed Linux distro coverage.

Architecturex86_64.
Kernel4.18 or later. Ships gated at 5.16.
Packaging.deb, .rpm, Helm chart for Kubernetes nodes, tarball for air-gapped installs.

Table 2a · Platform coverage

PlatformBase kernelStatus
RHEL, Rocky, Alma 95.14Supported
Amazon Linux 20236.1Supported
Ubuntu 24.04 LTS6.8Supported
Ubuntu 22.04 LTS5.15Supported
Debian 126.1Supported
RHEL, Rocky 84.18Supported*
Amazon Linux 25.10Supported*
Bottlerocket, Flatcar, Talos, COS5.10+Not supported
Fargate, EKS on Fargate, Snowpark Container ServicesNot supported

Table 3 · Scalability, recommended maximums

Firewall appliances per VPC or VCN1
Hosts per appliance128*
Appliances per fabric8, across VPC, VCN, region and provider boundaries*

Availability

Where and how to get it

CloudsAWS and GCP today.* Maya is built for cloud deployments and runs inside your own VPC or VCN.
StatusLimited availability.* Design partner slots are open now. Email contact@mayagentic.com.
MarketplacesPlanned. Cloud marketplace listing is the eventual distribution path.
Research EditionFree for universities, colleges and labs.* Programme details, or email research@mayagentic.com.
PricingOn request. Email contact@mayagentic.com with your fleet shape and we will scope it with you.

Notes

*
Beta-stage detail. Availability, capacity and platform coverage reflect the current beta and are expected to expand.
Under development. Subject to change. Not a commitment of timing or functionality.

On the roadmap

ABR · Agent-Based Routing

Policy-based routing selects a path from a prefix. ABR selects it from the agent: which region, which provider, which egress point, decided per agent from the declaration you already wrote. Data residency becomes a routing decision rather than an audit finding.

aiQoS, per-agent traffic shaping, is also on the roadmap.

The vision

Make every agent visible. Governable. Accountable.

Design partner, or buy. Tell us the shape of your fleet: how many hosts, which cloud, and what your agents are reaching today.

Talk to us White papers

Cookies

We use analytics cookies to see how this site is used so we can make it better. Nothing is stored until you say yes. See our privacy policy.