Platform

An always-on platform your agents plug into.

Moneypenny is not another chat window. It watches your channels continuously, triages what matters, and hands signed-off work to whichever agent runner is plugged in this run — while the state, history, and decisions live one layer below all of them.

Five differentiators

What a reactive assistant has no reason to build

Five structural bets, each one a layer that only exists because the platform is always-on, cross-vendor, and built to outlast any one agent harness.

Eavesdropper

Every connected channel is watched continuously, without being asked. Signals get classified, entities extracted, and a ticket staged before anyone opens the thread.

Switchboard, an input device

The triage surface is not a dashboard to check. A five-second swipe cancels in-flight work, reprioritizes the queue, and feeds the decision straight back into the pipeline.

Agent-mesh as transport

Claude Code, Codex, and pi are not just where work executes — they are where you touch the platform. Sign from a phone, close from a terminal: the mesh carries the same interaction everywhere.

Multi-stage skillsets

A single skillset registers a watch-signal, an enricher, an execution verb, a datasource, and an outbound feedback hook at once — one plugin across five stages, not five separate integrations.

Subsumption-resistant

State and history live one layer below whichever agent is running. Every stronger model release becomes a dependency upgrade for this platform, not a competitor to it.

Competitive position

Different axis, not a bigger number

Ten axes, rebuilt on-brand from the internal scorecard. Moneypenny leads passive intelligence, human-in-the-loop triage, cross-vendor orchestration, multi-stage plugins, and subsumption resistance — and it concedes channel breadth, community, memory depth, and voice. Self-improving (measured substrate) sits low-mid: it built the measurement layer most systems skip, but hasn't closed the loop into autonomous improvement.

Scorecard comparing Moneypenny against OpenClaw, a reactive gateway, and Hermes, a self-improving framework, across ten axes, each scored out of 10. Moneypenny leads passive intelligence 9, HITL triage 9, cross-vendor orchestration 8, multi-stage plugins 9, and subsumption resistance 9 — both rivals score 4 or below on those five. Moneypenny trails on channel breadth 3, community 0, memory 5, and voice 3. Self-improving, measured substrate, sits at 5: above a naive 2 because a live eval and reward ledger is real and partially wired, below 'ahead' because the loop from measurement to actual improvement isn't closed, and autonomous generation plus community are conceded.
Axis Moneypenny OpenClawa reactive gateway Hermesa self-improving framework
Passive intelligenceLeads
9/10
1/10
1/10
HITL triageLeads
9/10
2/10
1/10
Cross-vendor orchestrationLeads
8/10
4/10
2/10
Multi-stage pluginsLeads
9/10
3/10
2/10
Subsumption resistanceLeads
9/10
3/10
4/10
Self-improvingmeasured substrateIn progress
5/10
4/10
9/10
Channel breadthConcedes
3/10
9/10
5/10
MemoryConcedes
5/10
6/10
8/10
VoiceConcedes
3/10
7/10
3/10
CommunityConcedes
0/10
10/10
7/10

An internal scorecard, not a benchmark — these are our axes and our read of OpenClaw and Hermes, scored by us. The receipts behind every claim live on the guarantees page.

Multi-stage skillsets

One skillset, five hooks

A skillset is not a single-stage plugin invoked on request. It registers across the pipeline at once — a watch-signal on intake, an enricher on triage, a verb on the execution engine, a datasource on entity extraction, and an outbound hook back to a channel.

skillset: career-partner — one plugin, five hooks Watch-signals Eavesdropper stage flags recruiter-pattern emails Enrichers Entity extraction extracts company, role, comp Verbs Execution engine draft-cover-letter fires when you sign Datasources External lookups LinkedIn profile lookup Outbound Channel feedback syncs outcome to Notion RUNNING HANDLED

The spine is purple everywhere on this site for exactly one reason: it is the color reserved for a skillset extension point, nowhere else. friendship-graph and media-finder cross the same five columns.

Coordination substrate

The engineering underneath the pitch

Three claims about how this platform holds itself accountable — each one backed by a mechanism, not a policy.

Evidence, mechanically
Nothing is done without evidence.
a commit that closes work without receipts is rejected by a pre-commit gate — not by policy
Packets, not vibes
Work is packets, not vibes.
every unit gets an atomically-allocated id, steps, and acceptance criteria before an agent may start
Self-interrupting
The system interrupts its own mistakes.
nearly a hundred regex-triggered rules stop an agent mid-action when it's about to repeat a documented failure
Brand kit

Downloads coming

The mark, the wordmark, and the icon system this platform draws from.

C1 mark
MONEYPENNY · AI Wordmark lockup
Icon set v2

Brand kit — packaged, versioned downloads land here when the release is cut.

Go deeper

Two more angles, one demo

See the demo Real Switchboard UI · sample data · nothing to sign in

Honest about what's not here yet: the brand kit above is a preview — packaged, versioned downloads land here when the release is cut. The scorecard is a rebuilt internal self-assessment, not a third-party benchmark — its rival columns describe categories of competitor, not a named product. The multi-stage skillset diagram illustrates career-partner's real hook points; friendship-graph and media-finder register fewer of the five today.