foundation.protocols.*

Event Families

All events use the foundation.protocols.* namespace. No MSC required — custom namespaced events are a blessed Matrix extension mechanism.

foundation.protocols.data.*

Data Commons

4 events (3 timeline, 1 state)

Consent-gated data sharing. Contribution, consent, withdrawal, quality assessment. Ostrom-governed commons with explicit, revocable consent at the protocol level.

foundation.protocols.ai.*

AI Governance

17 events (10 timeline, 7 state)

Vendor-neutral governance for any AI agent. Intention/Decision/Effect audit trail (ESAA pattern), policy gates, kill switch, cost tracking, model registry, risk assessment, transparency cards.

foundation.protocols.ai.claude.*

Claude Session Recording

42 events (40 timeline, 2 state)

Complete Claude Code session recording: prompts, responses, thinking, tool calls, MCP interactions, approvals, file changes, git operations, cost tracking, multi-agent coordination.

foundation.protocols.ai.gryph.*

System Hook Observation

15 events (15 timeline)

Independent system-level observation of AI coding agent actions via native hooks. Tool call interception, file change hashing, security block/guidance decisions, actual cost from transcripts, subagent lifecycle tracking. The execution audit layer — parallel to claude.* self-report.

foundation.protocols.ai.observation.*

Bridge Observation Layer

15 events (15 timeline)

Bridge-native observation of AI agent actions: tool use, file operations with content hashing, command execution, security decisions, cost snapshots, privacy sensitivity, subagent lifecycle. The Kotlin bridge's own audit trail (AGPL-3.0) — parallel to gryph.* and claude.*.

foundation.protocols.ai.claude.hook.*

IAS Hook Enforcement

5 events (5 timeline)

Gate enforcement decisions from Claude Code hooks: which rules were evaluated, what was blocked or allowed, session lifecycle, and subagent spawn/completion tracking with inline agent attribution.

foundation.protocols.ai.certification.*

Verifiable Execution Certification

4 events (4 timeline)

Dual-observer correlation verdicts: PASS when agent self-report matches independent system observation, FAIL on discrepancy, GAP for missing signatures. Session-level CERTIFIED / FLAGGED / PARTIAL judgment.

foundation.protocols.ai.hopsworks.*

Hopsworks ML Lifecycle

37 events (36 timeline, 1 state)

Complete ML lifecycle recording for Hopsworks Feature Store, Model Registry, and serving. Feature engineering, model training, deployment, governance, cost tracking, dual-bridge Claude correlation.

foundation.protocols.ai.ansvar.*

Ansvar Legal MCP Recording

11 events (9 timeline, 2 state)

Complete MCP interaction recording for Ansvar legal and regulatory servers. Tool calls, resource access, citation extraction, session lifecycle. Data stays home — only metadata crosses the bridge.

foundation.protocols.ai.cost

Cost Tracking

1 state event

Vendor-agnostic, multi-currency, per-user cost accumulator. State key = Matrix user ID. Supports SEK, EUR, USD, INR, CNY. Space-level aggregation across rooms.

foundation.protocols.eudr.*

EUDR Compliance

11 events (9 timeline, 2 state)

EU Deforestation Regulation (2023/1115): plot geolocation, satellite deforestation verification, chain-of-custody, harvest records, Due Diligence Statement workflow, country benchmarking.

foundation.protocols.legal.*

Legal Workflows

18 events (14 timeline, 4 state)

Legal marketplace: briefs, proposals, escalation, lawyer seal, case assignment. Professional privilege rooms. Per-jurisdiction spaces. Bar council verification.

foundation.protocols.ai.ias.claude.*

DICSTAMACH Context State

8 events + 2 verify sub-types

Introspection layer. Dynamic Interactive Claude State Machine: session lifecycle, domain loaded/unloaded, consent-gated garbage collection, pressure-threshold signals. Cross-verified by gryph-based hooks observing STATEOFCLAUDE.md writes.

Design Principles

The protocol extensions follow these architectural principles.

Example: AI Intention Event

Before a high-risk operation, the agent proposes its action for approval.

{
  "type": "foundation.protocols.ai.intention",
  "content": {
    "intention_id": "int_01ABC",
    "session_id": "sess_01ABC",
    "agent_type": "claude-code",
    "agent_model": "claude-sonnet-4-20250514",
    "proposed_action": "execute_shell_command",
    "description": "Delete the dist/ directory for a clean build",
    "parameters": { "command": "rm -rf dist/" },
    "risk_level": "high",
    "requires_human_decision": true,
    "policy_ref": "$ai_policy_state_event_id"
  }
}

If ai.policy requires approval for this tool, the bridge holds execution until an ai.decision event (approved/denied) arrives. The outcome is recorded as ai.effect.

Implement

No special server support needed. Any Matrix homeserver accepts custom namespaced events.

#foundation-protocols:matrix.openearth.network

The Protocols Foundation

A vendor-neutral standards body maintaining the foundation.protocols.* namespace. Currently initiated by VakeWorks. Seeking co-maintainers and organisations interested in domain-specific Matrix protocol extensions.

The protocol spec is separate from any implementation. openearth.network provides reference implementations. Any organisation can implement foundation.protocols.* events on their own Matrix infrastructure.