Architecture

The SovereignClaw architecture is built for AI agent runtime security: deterministic execution gating, 20 Rust crates, 829+ tests, and 9 formal security properties.

SovereignClaw's architecture treats every LLM-proposed action as untrusted input. The seven-stage execution pipeline turns model output into a deterministic, policy-evaluated decision before any side effect can occur. For teams evaluating enterprise AI governance, this page shows how runtime security, evidence generation, and operational control fit together in one system.

This architecture is designed for organizations that need more than best-effort AI guardrails. Instead of filtering or post-hoc review, SovereignClaw canonicalizes intent, verifies facts, assigns risk, and binds any permitted execution to signed artifacts and receipts. Pair this architecture view with the security properties, compliance coverage, and deployment tiers to understand the full operating model. Published on SSRN (ID 6290760). Patent applications pending: USPTO 74981727 · 74483691 · 73809451 · 72763061.

Execution Pipeline

Every agent action passes through a deterministic 7-stage pipeline before any execution can occur. No shortcuts. No bypasses.

Stage-by-stage execution flow

Intent
Canonical IR
Fact Infer
Iron Gate
Adapter
Receipt
Merkle Ledger

Risk Tier Classification

Every action is classified into one of four risk tiers. The gate behavior is determined by the tier, not by the LLM's self-assessment.

Policy behavior by tier

TierNameExampleGate Behavior
T0Observels -laAuto-allow
T1StandardWrite app configAllow with signed receipt
T2ElevatedRestart production serviceRequires threshold signatures (m-of-n)
T3SovereignDelete IAM / DB / infraMechanical refusal — blocked by default

Crate Architecture (20 Crates)

The crates are grouped around three jobs: immutable intent representation, enforcement and authorization, and enterprise runtime operations. That separation is what lets SovereignClaw map execution controls cleanly into audit and compliance evidence.

Core, control-plane, and runtime crates

CrateRole
libs/coreImmutable SovereignIR schema, canonical hashing, execution graph
libs/gatePolicy engine: fact inference, tier classification, threshold signatures, WASM plugin sandbox, revocation check
libs/adapterAttested runtime: 10-step verification, nonce replay protection, AEAD credential store, SQLite revocation registry
libs/receiptAppend-only Merkle-anchored ledger of signed authority receipts
libs/tenantMulti-tenant isolation: context hashing, quotas, cross-tenant denial
libs/vaultPer-tenant, per-environment credential vaults with lease-gated access
libs/cryptoThreshold signature collection (m-of-n) and key rotation
libs/identitySSO/SCIM identity bridge: IdP group → approval quorum mapping
libs/approvalPersistent async approval workflows with quorum, TTL, escalation
libs/enterprise16 enterprise skill modules with tier classification (T0–T3)
libs/skill_registryVerified manifests, publication state, quarantine, intake freeze, tenant allowlisting
libs/skill_scannerWASM bytecode behavioral analysis — flags network, file-write, env-read imports against declared scope
libs/meshEd25519-signed inter-agent envelopes, delegation chains with scope attenuation, propagation depth limits
libs/agentLLM orchestration loop, provenance-tagged memory, context injection boundary, swarm execution runtime
libs/gatewayHTTP control plane with deployment attestation, compliance metrics (CEF/SIEM), production mode profile
Request Early Access

Frequently Asked Questions

What is the SovereignClaw execution pipeline?
Intent → Canonical IR → Fact Inferencer → Iron Gate → Adapter → Receipt → Merkle Ledger. Every agent action passes through this deterministic pipeline before execution.
How many crates make up SovereignClaw?
20 Rust crates covering core IR, policy gating, adapter verification, receipt ledger, multi-tenant isolation, credential vaults, threshold crypto, identity bridges, approval workflows, enterprise skills, skill registry, skill scanner, agent mesh, agent orchestration, and HTTP gateway.
What are the SovereignClaw risk tiers?
T0 (Observe) — auto-allow. T1 (Standard) — allow with signed receipt. T2 (Elevated) — requires threshold signatures (m-of-n). T3 (Sovereign) — mechanical refusal, blocked by default.