CLAWSOLATOR ALPHABeta release planned · License under considerationRead what is verified
XERXES SI / SECURITY ENGINEERING

Clawsolator Engineering Evidence: Claims, Controls and Verification

Technical leaders and researchers should not have to guess which claims are implemented, planned, upstream, or independently tested. Start here.

Independent engineering commentary by XERXES SI · Updated November 1, 2026 · Claims separated from roadmap

What an enterprise reviewer can actually verify

Product identity

Clawsolator means Claw + Isolator. It is a XERXES SI project for governed operations around AI agents. It is not the old Captain Claw game and not an OpenClaw fork by implication.

Read the evidence and analysis →

Actual CLI syntax

The inspected XMAN package supports ./xman.sh autosetup; the older art string --autosetup was wrong. Test behavior on the targeted host before claiming success.

Read the evidence and analysis →

What the software does today

Manager-mediated rootless Podman operations, bounded special host requests, approval workflow and action logs as present in the reviewed source.

Read the evidence and analysis →

What is not certified

No third-party certification, no general security guarantee, no verified OpenShell integration, no all-plugin malware scanning claim.

Read the evidence and analysis →

Investor and acquisition due diligence

For a serious strategic discussion, publish repeatable measurements: setup completion rates, time to review/resolve host requests, policy-bypass tests, restart recovery, CPU/RAM caps, failure isolation, and audit event completeness. Include the target environment and raw methodology. An impressive interface invites a conversation; a reproducible test earns the next meeting.

Our promise is not that agents never fail. It is that we design the boundaries so failure can be understood, constrained, reviewed and improved.

Strong claims deserve strong evidence.

Inspect the controls, verify the boundaries, and ask what happens after a failure—not merely before it.

Explore the security lattice →Read the architecture →

CANONICAL TRUST BOUNDARY

Agents request. XMAN decides. Operators authorize exceptional host work.

Each registered agent uses the authenticated requester API through the trusted Gateway bridge. The XMAN management daemon governs policy, resource admission and durable outcomes through its private Unix-socket interface. The operator API is separate; the master coordinates but does not become the operator. The future SysOp and Security Officer daemons would be separate, permissioned services, not current Alpha functionality.

NEW RESEARCH / DOCUMENTED OPERATOR FRUSTRATIONS

What users asked the systems to do

Firsthand issue reports, exact failure symptoms, the proposed engineering response and explicit verification limits.

Managed updates: claim vs proof →Public reports and House of Order →