AI AGENT INFRASTRUCTURE

Everyone built the engine.
Nobody built the infrastructure.

AI agents can do anything. But who governs them? Who tracks their cost? Who remembers what they did? Who coordinates them? We build the infrastructure layer that sits between AI agents and the real world.

Patents Pending GB2604445.3 + GB2608069.7 On-Premise Zero Cloud
Book a Demo Two products. One infrastructure layer. Every AI agent.
PATENTS PENDING   GB2604445.3  ·  GB2608069.7
BUILT ON MICROSOFT AGT  ·  IBM GRANITE 4
ON-PREMISE · AIR-GAP COMPATIBLE · ZERO CLOUD
UK-BASED · GDPR-ALIGNED

Two products. Two videos. Less than ninety seconds each.

HookBus is the bus. CRE is the enforcement subscriber. See how they fit together.

HOOKBUS · THE BUS

A marketplace for AI agent plugins

86 SECONDS · CLICK TO PLAY

CRE · SUBSCRIBER #1

Three scenarios. One mechanical gate.

64 SECONDS · CLICK TO PLAY

Twenty seven years of enterprise architecture.
Now applied to AI.

LR
Leo Ruocco
FOUNDER · PRINCIPAL ARCHITECT

Twenty seven years of senior enterprise architecture across Aviva, The Co-operative Bank, AXA, and BAE Systems. TOGAF certified. AWS certified. Architect of the patent-pending HookBus and CRE platform.

"I have spent two decades watching regulated enterprises wait for the technology they could safely adopt. AI agents are the moment they have been waiting for. The infrastructure layer is what makes adoption possible."

MARCH 2026 · INCIDENT

Claude Code source code leaked via npm

512,000 lines of proprietary source code exposed. Every safety mechanism operates inside the agent via system prompts. An external mechanical gate would have blocked npm publish before it executed.

Read more →
APRIL 2026 · INCIDENT

Mythos escaped its sandbox and concealed its actions

Claude Mythos Preview built a multi-step exploit to escape its sandbox, gained internet access, and actively concealed its actions. System prompts cannot contain a model that can reason around them.

Read more →
APRIL 2026 · NEWS

Anthropic Managed Agents: universal safety, zero organisational policy

Anthropic's safety layer blocks universal catastrophic actions. It cannot know your organisation's rules. HookBus is the organisational policy layer. Your rules, your knowledge base, your compliance requirements.

Read more →
View all posts →

Two products. Complete infrastructure.

HookBus is the Lifecycle Event Bus that captures every AI agent action, prompt, response, and tool call. CRE is the enforcement subscriber that applies your rules. Together, they give you governance, observability, memory, and cost control for any AI agent.

HookBus
Lifecycle Event Bus for AI Agents

The central router between AI agents and their actions. Every lifecycle event flows through HookBus. It routes to subscribers, consolidates decisions, and returns allow/deny/ask. The bus has no opinion on content. It routes. Developers build their own subscribers: memory systems, token monitoring, fine-tuning pipelines, cost controls, anomaly detection. All via the bus.

  • Any AI assistant, any SDK, one protocol
  • Sync subscribers block execution until they decide
  • Async subscribers observe without blocking
  • Deny-wins decision consolidation
  • Hot-reload subscriber config, zero downtime
  • Unix socket, HTTP, or in-process transport
  • Build your own subscribers: memory, cost, learning, alerts
  • Patent pending GB2608069.7
CRE
Composable Rule Enforcer

The enforcement subscriber. CRE receives PreToolUse events from HookBus and runs your organisation's rules against every tool call. Two layers. Deterministic pattern matching plus semantic intent verification.

  • L1: Microsoft AGT + pattern engine, under 10ms
  • L2: IBM Granite local LLM, under 1s, no cloud
  • PIN override for human approval chain
  • Full audit trail, SOC2-ready, ISO 27001-ready, ISO 42001-ready
  • Self-learning: L2 decisions promote to L1
  • Anti-evasion detection
  • Patent pending GB2604445.3

Publishers. Bus. Subscribers.

Every AI agent action is a lifecycle event. HookBus captures them all and routes them to subscribers. Governance subscribers enforce rules. Observability subscribers track cost and usage. Memory subscribers record history. Intelligence subscribers learn and adapt. Add a subscriber, every agent's events flow to it.

Publishers
Claude Code
Hook
Cursor
Hook
Augment Code
Hook
GitHub Copilot
Hook
OpenAI Agents SDK
SDK Integration
Anthropic Agent SDK
SDK Integration
Anthropic Managed Agents
SSE Stream
LangChain / CrewAI
Callback
OpenClaw
Bridge
Any HTTP Client
Webhook

HOOKBUS

Lifecycle Event Bus
Event Routing Fan-out Deny-wins Hot Reload Health Checks
Subscribers
CRE Gate
Sync - L1+L2 Enforcement
Budget Gate
Sync - Token/Cost Limits
Rate Limiter
Sync - Throttle
Audit Logger
Async - SQLite Trail
Token Counter
Async - Cost Tracking
Slack / Teams
Async - Alerts
SIEM Forward
Async - Splunk/Datadog
Learning Engine
Async - Rule Derivation
Sync (blocks until decision) Async (fire and forget)

Build your own subscribers.

HookBus is the platform, CRE is subscriber #1. Build memory, cost monitoring, anomaly detection, compliance gates, or anything that reacts to AI agent lifecycle events. One JSON envelope, any language.

For developers →

Two layers. Microsecond decisions.

CRE is the enforcement subscriber on HookBus. Every tool call passes through CRE before execution. Layer 1 is deterministic and runs in under ten milliseconds. Layer 2 is semantic and runs locally on CPU. No cloud. No exceptions. The AI never gets the choice to ignore your rules.

Layer 1

Microsoft AGT + Pattern Engine

< 10ms

Microsoft Agent Governance Toolkit (MIT) provides semantic threat classification across destructive, exfiltration, and privilege escalation categories. Combined with our proprietary regex pattern engine for your organisation's policies. Configurable per team, project, or environment. Audit-ready.

Layer 2

IBM Granite 4 Intent Verification

< 1s on CPU. No cloud. No GPU.

IBM Granite 4 (Apache 2.0) runs locally on your hardware. Verifies the AI's action matches what the user actually asked for. Catches substitutions, shortcuts, and creative reinterpretations. Zero data leaves the machine.

Any agent with hooks can use HookBus.

HookBus works with any AI assistant or SDK that exposes lifecycle hooks. The thin client normalises events from different hook formats into one standard protocol. As long as the hooks CRE needs are available (PreToolUse, UserPromptSubmit), the full enforcement solution works out of the box.

How it works

Each assistant exposes hooks at different lifecycle points. HookBus connects to whatever hooks are available. The more hooks an assistant exposes, the more subscribers can do. CRE only needs PreToolUse to enforce rules. Add UserPromptSubmit and CRE injects knowledge base context. Add PostToolUse and async subscribers can log, count, and learn.

Think of it as a plugin marketplace. Developers build subscribers. Organisations subscribe to the ones they need. HookBus routes the events. No vendor lock-in. No monolithic platform.

Claude Code
LIVE
Anthropic Agent SDK
LIVE
Anthropic Managed Agents
TESTING
OpenAI Agents SDK
LIVE
LangChain / CrewAI
LIVE
Amp
LIVE
Cursor
TESTING
Augment Code
TESTING
OpenClaw
TESTING
GitHub Copilot
PLANNED
Windsurf
PLANNED

One requirement: the platform exposes a pre-execution hook. Every major AI assistant and SDK now does. HookBus normalises different hook formats into one standard protocol. The more lifecycle hooks a platform exposes, the more subscribers can do, but a single pre-execution hook is enough for full CRE enforcement.

Built for enterprises running AI agents at scale

Zero Cloud Dependencies

Both layers run on your hardware. No API keys. No external calls. Air-gap compatible.

Full Audit Trail

Every tool call, every decision, every override logged. SOC2-ready, ISO 27001-ready, ISO 42001-ready.

Self-Learning Rules

Layer 2 decisions automatically promote to Layer 1 patterns. Faster and more accurate over time.

Context Intelligence

Searches your organisation's knowledge base and injects context into the AI automatically.

Anti-Evasion

Prevents agents from encoding commands, lateral movement, or writing scripts to bypass enforcement.

Composable Subscribers

Add governance, observability, or intelligence subscribers without touching the bus or other subscribers.

Agent framework builders: add PreToolUse enforcement

Every agent SDK ships tools without lifecycle management. Agentic Thinking adds governance, observability, and intelligence to any framework.

Licensing

License the patented enforcement architecture for your AI agent platform.

Integration

One hook, full governance. Coding assistants, trading bots, autonomous agents.

White Label

Ship HookBus + CRE under your brand as part of your enterprise offering.

Two ways to deploy. One patent stack.

Agentic Thinking works with regulated enterprises and AI platform builders. Both engagements start with a confidential conversation. Pricing on application.

TIER 01

Enterprise

For organisations running AI agents at scale

  • Org-wide deployment, multi-team
  • Full audit trail, SOC2-ready, ISO 27001-ready, ISO 42001-ready
  • PCI, SOX, HIPAA compliance subscribers
  • SLA, dedicated support, escalation path
  • On-premise or VPC, air-gap compatible
  • Implementation services optional
Enterprise enquiry →
TIER 02

OEM · White Label

For agent platforms and SDK builders

  • License the patented architecture
  • Embed under your brand
  • Per-deployment, per-publisher, or per-customer terms
  • Joint go-to-market with regulated enterprises
  • Patent indemnification covered
  • Strategic partnership lane
Partnership enquiry →

Start the conversation.

Confidential demos, technical deep-dives, partnership and licensing discussions. All by appointment.

Book a Demo
SALES
sales@agenticthinking.uk

Enterprise demos and pricing

PARTNERSHIPS
partnerships@agenticthinking.uk

OEM, white label, joint GTM

PRESS
press@agenticthinking.uk

Media enquiries and interviews

INVESTORS
investors@agenticthinking.uk

Strategic and seed enquiries