Runtime support audit

Where each agent runtime stands against AgentHook v0.2.

Candidate tiers show current hook coverage. Platinum is the high-assurance target being implemented through the reference agentic runtime and conformance work.

Where each agent runtime stands today.

A current audit of which hook surfaces each major agent runtime exposes. Candidate tiers show the as-is Bronze/Silver/Gold coverage available today. Platinum is the to-be high-assurance profile and is not used to score current publishers yet.

Coming soon: HookBus Agent.

HookBus Agent is being built as the open-source reference runtime for governance-native AgentHook execution. It is not required for conformance; it is a proof object for the high-assurance profile.

Read the product note →

Audit method: direct inspection of each runtime's published hook surface and public Agentic Thinking publisher repositories as of 19 May 2026. Gold candidate and Silver candidate mean the runtime currently exposes enough hooks for that as-is v0.2 coverage profile. Platinum means the future high-assurance target after the relevant AHP drafts and conformance test harness are accepted. Runtime providers may self-attest by Pull Request to the AgentHook repository. Self-attested rows will be marked accordingly. This audit is for technical interoperability comparison, not procurement guidance. Next scheduled review: 2 June 2026, then fortnightly while publisher coverage is changing.

Runtime
UserPromptSubmit
Pre / Post LLMCall
Pre / Post ToolUse
Reasoning capture
Candidate tier
Status
AgentHook Conformance Fixturereference fixture for the AgentHook standard
yes
yes / yes
yes / yes
yes
Platinum target
Reference fixture for Platinum target
GitHub
HookBus AgentAgentic Thinking reference implementation
yes
yes / yes
yes / yes
yes
Platinum target
Example Platinum runtime under construction
GitHub
HermesNousResearch
yes
yes / yes
yes / yes
yes
Gold candidate
Publisher shipped; conformance pending
GitHub
OpenCodeopen source
yes
yes / yes
yes / yes
yes
Gold candidate
Publisher shipped; conformance pending
GitHub
Claude CodeAnthropic
yes
no / no
yes / yes
partial
Silver candidate
Publisher shipped; conformance pending
GitHub
Codex CLIOpenAI
yes
no / no
partial / partial
partial
Silver candidate
Publisher shipped; conformance pending
GitHub
AmpSourcegraph
yes
no / no
yes / yes
no
Silver candidate
Publisher shipped; conformance pending
GitHub
OpenClawopen source
no
no / output only
yes / yes
no
Partial shipped
Publisher shipped; partial runtime surface
GitHub
Gemini CLI, Cursor, OpenAI Agents SDK, GitHub Copilot CLI, Cognition Devinpublisher pending
.
.
.
.
Pending
Pending

Pending rows will be filled as each runtime's hook surface is reviewed and validated against the conformance test suite. Self-attested rows and test harness verified rows will be marked accordingly. Microsoft Agent Governance Toolkit is tracked as a control/subscriber layer, not as an agent runtime publisher.