HookBus is the platform. CRE is subscriber #1. The bus has no opinion on what subscribers do. Build anything that reacts to AI agent lifecycle events. Memory, cost, learning, alerts, governance, compliance. Any service that can read JSON over a Unix socket, HTTP endpoint, or Python class can be a HookBus subscriber.
HookBus carries every lifecycle event from every agent. Subscribers can act on those events any way you need. Governance is one category. Not the whole story.
Allow, ask, deny on every tool call. Deterministic rules, contextual reasoning, data-loss prevention. Stop bad actions before they execute.
Session recall across interactions. Knowledge injection at the start of every conversation. Agents act with current organisational context.
Every event, every decision, logged with full metadata. Exportable to SIEM. Answers "show me every action across every agent last Tuesday".
Multiple agents on the same estate. File locking so two agents don't collide. Deferred mailbox so agents hand work to each other through the bus.
Fire Jira tickets, Slack / Discord / Teams messages, PagerDuty incidents, WhatsApp, email, any webhook. One normaliser subscriber, YAML-configured, zero custom code.
Token cost per agent per team. Latency and anomaly detection. Capture every tool call as fine-tune data, or distil behaviour into smaller local models.
The production subscribers Agentic Thinking ships on the bus. All HTTP or Unix-socket subscribers. No SDK lock-in. Each one is a few hundred lines of Python, plugged into the bus and replaceable.
Two-layer rule enforcement. L1 deterministic regex in milliseconds, L2 contextual reasoning via an external LLM with conversation, preferences, and persistent enforcement memory. The moat.
Retrieves the most relevant internal policy, runbook, or compliance context for each event. Injects it as preprompt so the agent acts with current organisational knowledge in-context.
Tracks prior interactions per user, per agent, per session. Provides context for L2 reasoning and downstream subscribers. Evidence of standing permissions and historical decisions.
Blocks or redacts PII, credentials, PCI, PHI, and financial data before it crosses the agent trust boundary. Bidirectional: outbound on PreToolUse, inbound on PostToolUse.
Structured audit log of every event and every decision. Who, what, when, which subscriber decided, why. Exportable to SIEM. Answers "show me every destructive action across every agent last week".
Fast L1-only regex gate. Sub-millisecond decisions. For high-volume agents that need deterministic enforcement without the cost of LLM reasoning on every call.
Coordinates multiple agents working the same estate. File locking so two agents do not edit the same file. Deferred mailbox injection so agents hand work to each other through the bus. Agent registry from live event stream.
Any lifecycle event, any destination, zero code. One YAML-configured subscriber that speaks Slack, Discord, Teams, Jira, PagerDuty, Datadog, Splunk, Email, WhatsApp, or any webhook. New destination? Add a line of config.
HookBus subscribers are services that read a lifecycle event from stdin (or a socket) and write a decision back. There is no SDK. There is no framework lock-in. There is one envelope.
Sync subscribers block execution until they decide. Return allow, deny, or ask. Deny wins if any subscriber denies.
Async subscribers observe events without blocking. Use them for memory, audit logs, cost tracking, alerts, and SIEM forwards.
Transport options: Unix socket, HTTP endpoint, or in-process Python class. Hot-reloadable config. Health checks per subscriber.
A reference AI agent with 6 gated tools (bash, read, write, edit, glob, grep). Every tool call is mechanically gated through HookBus before execution. Works with any OpenAI-compatible LLM. Plug in your API key, point at the bus, and your agent is governed. Open source. MIT licence.
One subscriber that turns HookBus lifecycle events into whatever format the destination expects. Slack webhook. Jira REST. PagerDuty incident. Datadog metric. Splunk event. WhatsApp message via Twilio or Meta Cloud. Generic webhook. All from one container, configured with YAML. No custom integration code.
A subscriber that invokes reusable skill modules on behalf of any agent. One skill library, used by every agent on the bus. Claude, Cursor, Amp, a custom Slack bot: all trigger the same skills through the same events. No per-agent plugin code.
HookBus is closed source for now while the patent is pending, but we work directly with design partners to build subscribers against the bus. If you have a use case, get in touch.