CAIN-42 MCPGate

AGENTIC AI 75 · #6

Single-prompt coordination of specialised agent teams

Google previewed an Antigravity swarm feature with parallel workspaces, specialised responsibilities and checking agents.

Last reviewed 2026-11-11

Agentic AI 75 / #6

LIVEMoat 2 · Security-Context ContinuityBundle · Swarm & Multi-AgentStream 2

2026 status: Product preview · Category: Agent orchestration

The 2026 development

Google previewed an Antigravity swarm feature with parallel workspaces, specialised responsibilities and checking agents.

The governance gap

A planner that can spawn workers and checkers can also spawn a worker with more authority than the planner holds, or let a checker approve its own sibling. Parallelism multiplies the places where scope can drift.

Where CAIN-42 fits: Moat 2 — Security-Context Continuity

Core question: Does authority survive every boundary? Identity, scope and delegation are carried across tools, agents, memories and systems.

Make delegation attenuation structural: a child capability can only narrow the parent's scope, lifetime and resources. CAIN's execution-chain capability type refuses a handoff that widens scope or extends life, regardless of what the planner says.

How the wiring works

  1. Issue the planner a capability with explicit scope, destination and expiry.
  2. Derive each worker capability from the parent, allowing only narrowing.
  3. Require the checker to be a different identity from the worker it checks.
  4. Record the delegation tree and verify it after the run.

What is real today

LIVE A public route in this deployment exercises this mechanism today, within its stated scope.

The hosted demo proves attenuation and collusion checks on fixed presets. It does not operate Antigravity or any Google product.

Component in this repositoryWhat the module says it is
cain/execution_chain/capability.pyAttenuated, audience/destination-bound cross-system execution capability (Evolution 10, Phase 4).
cain/execution_chain/multiagent.pyMulti-agent coordination without false security claims (Evolution 10, Phase 9).
cain/argus/envelope.pyCAIN ARGUS — Behavioral Authority Envelope (Prompt 14, section 6).
keystone/swarm.pySWARM KEYSTONE: Multi-agent swarm delegation audited, Claude re-architects, formal DAG & attenuation proved, signed.

Descriptions are the first line of each module's own docstring, read without importing it. A module path is a pointer into this repository, not a hosted endpoint. Its existence is checked by the test suite; its status for this use is the label above.

Check it yourself

Commercial package

OfferSwarm Delegation Audit
BuyerAgent-orchestrator vendors and enterprise platform teams
Price (proposal)$3,500–$7,500 per audit
BundleSwarm & Multi-Agent — Delegation you can follow across every hop.
Operator streamStream 2 of the 10-stream operator playbook

Agent orchestrator vendors, research labs, enterprise platform teams is the bundle buyer. The entry offer for this bundle is Swarm delegation audit; collusion and drift review; the range is $3,500–$7,500 per audit; $2,500–$4,000/month retainer. A price on this page is a proposal, not a validated rate, and no customer is claimed.

Buy this as a product or service

CAIN-A75-006 — Swarm Delegation Audit DELIVERABLE

A bounded engine run on the buyer's sample: findings, a written report, and a SHA-256 artifact manifest. The manifest is unsigned: it is not a signature and not an attestation.

Kind: Assessment · Price (proposal): $3,500–$7,500 per audit · Lead time: 5 business days.

Open the product page · all 75 products

What this page does not claim

What this page is not. CAIN-42 is not affiliated with, endorsed by, integrated into, or shipped with the organisation named in the 2026 item. The item is public context; the page describes how CAIN-42 would govern that class of capability. No page here claims a customer, a partnership, a certification, a patent, or a production integration. Prices are proposals. Built by a three-person team.

← #5 Open-world multi-agent mathematical discoveryAll 75#7 Digital twins for safe physical agent actions →