McPherson Governance for OpenClaw

See what your OpenClaw agents did before you give governance the power to stop them.

McPherson Governance evaluates supported tool activity against explicit policy and records what happened, what policy would have decided, what needs review, and what remains unknown.

The current public release operates in shadow mode. It has no authority to block, approve, deny, or rewrite your agents’ actions.

v0.7.3 public plugin Observa private beta open Shadow-only · Authority NONE
Know which one you are looking at

The public plugin and the Observa private beta are different products.

Public · Free · Distributed now

McPherson Governance OpenClaw plugin

  • A public OpenClaw plugin, currently v0.7.3, distributed through ClawHub
  • Account-free local agent and tool discovery
  • Non-authoritative AutoMap proposals and a local Governability Diagnosis
  • Shadow governance with local, private reports
  • Its own public version and release line
Private · Founder-assisted · Now open

Observa private beta

  • The broader Observa product for selected n8n and OpenClaw workflows
  • Capability and workflow mapping with human review
  • Structured governance evidence and review state
  • Independent verification of supported workflow outcomes
  • SHADOW_ONLY, no production control, no billing
Request Private Beta Access

The GitHub and ClawHub links above are the public OpenClaw plugin. They are not the distribution path for the full private Observa beta, which is onboarded directly with Blake.

Why activity logs are not enough

A tool event and governance evidence answer different questions.

Agent activity

“The refund tool ran.”

Governance evidence

“Who requested it, which policy applied, whether approval was required, whether the action completed, and whether the evidence is sufficient.”

Illustrative example only. It does not describe a specific production integration or claim that the current release observes every refund workflow.

How it works

Build evidence without overstating authority.

Shadow mode is designed to evaluate policy without actively controlling production actions.

  1. Agent proposesA supported tool action enters the configured path.
  2. Plugin observesAn attempt receipt and minimized metadata are produced.
  3. Policy evaluatesExplicit rules produce a non-authoritative shadow decision.
  4. Evidence is boundDirectly observed completion is correlated to the attempt.
  5. Observa explainsMeasured facts stay separate from assumptions.
  6. Operator reviewsGaps and exceptions become follow-up work.
Agent proposes. Policy decides. Runtime enforces. Observa explains and verifies. In the current public release and the private beta, policy decisions are recorded in shadow mode. Runtime enforcement is not active.
Current public plugin release

McPherson Governance v0.7.3

Public and verified Public release

Local V6 diagnostics

  • Account-free agent and tool discovery
  • Non-authoritative AutoMap proposals
  • Local Governability Diagnosis and private reports

Runtime guardrails

  • OpenClaw 2026.8.2 or newer required
  • Live observation targets exact audited builds; v0.7.3 is built and managed-install proven against 2026.8.2
  • Unconfigured tools stay local and make no network request

Verified release

  • Published archive digest equals a deterministic rebuild
  • Reproducible build with published provenance
  • Authority remains shadow-only
Proof

Operator proof and technical proof serve different readers.

Operator proof

What an operator needs to review

  • What was attempted
  • What completed
  • What policy would have decided
  • What needs review
  • What remains unknown
Technical proof

What the public release can substantiate

  • McPherson AI release verification for v0.7.3
  • An annotated tag pointing at the published release commit, with the release marked Latest
  • A reproducible build: the published archive digest equals a deterministic rebuild
  • A provenance record shipped in the package, binding it to its authorized source tree
  • Shadow-authority verification: authority NONE, enforcement OFF, active false, fixed in the plugin manifest
  • Public availability through ClawHub, with ClawHub’s own security audit for this listing reporting Safe
Free plugin and managed setup

Choose the level of help your environment needs.

Free OpenClaw plugin

For technical operators

For technical OpenClaw operators who can install, configure, map, and validate their own environment.

The public v0.7.3 release ships a unified local observa CLI with verified-email access requests alongside the existing pairing and lifecycle commands, and a reproducible build. Account-free local discovery, AutoMap proposals, and the local Governability Diagnosis were introduced in the v0.6.x line and remain available.

Install the Free Plugin
Founding Governance Setup

For operators who want a guided start

For operators who want McPherson AI to help map tools, define policy, review shadow evidence, and identify coverage gaps.

Request Founding Setup
Where the path stands

Observation first. Authority only after gates are verified.

Shipped

The v0.5 public line observed supported activity and produced shadow policy decisions and evidence.

Current

The v0.6 public line adds local discovery, AutoMap proposals, and Governability Diagnosis. The Observa private beta is now open for selected n8n and OpenClaw workflows, adding founder-assisted mapping, governance evidence, and independent verification of supported outcomes.

Later, gated

Bounded enforcement is introduced only after policy, runtime, approval, and evidence gates are verified. Nothing in the current release or beta grants execution authority.

FAQ

Questions to resolve before relying on the connector.

Does the current release block my agents?

No. The current release evaluates policy in shadow mode. Remote decisions have no execution authority, and the connector does not actively block, approve, deny, delay, or rewrite ordinary tool actions.

Is the Observa private beta the same as this plugin?

No. The plugin is the free, public, account-free OpenClaw connector. The Observa private beta is the broader product: it accepts selected n8n and OpenClaw workflows, is onboarded directly with Blake, and adds capability mapping review, structured governance evidence, and independent verification of supported workflow outcomes. Both are shadow-only today.

What data leaves my environment?

When enabled, the connector can send a closed allowlist of identifiers, class labels, one-way hashes, timestamps, and mapped metadata to the governance endpoint you configure. It does not send prompts, message bodies, tool parameters, file contents, credentials, customer records, or local receipt ledgers. Operator-chosen identifiers can themselves be sensitive, so naming and retention still require review.

What happens if the policy service is unavailable?

The connector remains non-blocking. A slow, malformed, absent, or hostile remote response can change the local observation record, but it receives no authority over the ordinary production action. Bounded queues and circuit behavior also mean some observations may be dropped and recorded as such.

Does it observe every tool?

No. Observation depends on supported OpenClaw hooks, correct mappings, selected tools, and the configured path. In the current public release, a tool without complete configured metadata remains local, makes no network request, and is recorded as a skipped observation. Activity outside the configured path may not be represented.

Can I use it without managed setup?

Yes. The free public plugin is intended for technical OpenClaw operators who can verify the package, configure the endpoint and private state paths, map tools, start disabled, and validate the evidence themselves. Review the current release notes before installing.

Does it certify compliance?

No. McPherson Governance does not certify compliance, security, safety, visibility, or completeness. Its evidence can support review, but the meaning and sufficiency of that evidence remain bounded by coverage and operator context.

What happens before enforcement receives authority?

Policy behavior, runtime integration, approval handling, evidence quality, failure behavior, and operator controls must be verified as explicit gates. The roadmap does not grant the current release authority it does not have.

How do I install or uninstall it?

Use the tagged public v0.7.3 package README: install through OpenClaw’s supported managed mechanism, configure it disabled, check status, and enable deliberately. Uninstall preserves receipts and does not revoke Hosted credentials — unpair first. The earlier standalone v0.6.2 lifecycle guide remains available for that historical release; from v0.7.0 onward this guidance lives in the package README.

What OpenClaw versions are supported?

The public v0.7.3 release declares OpenClaw 2026.8.2 or newer in its own package manifest, was built and managed-install proven against 2026.8.2, and refuses incompatible runtimes. Older 2026.6.x targets were supported by the historical v0.6.x line and are not the support target for v0.7.3. See the v0.7.3 package README for the current boundary.

McPherson Governance is an independent product and is not affiliated with or endorsed by the OpenClaw project.