§ Product

How Maxwell works.

A compiler-grade analysis engine built on the Truss platform. How it works, what it checks, and how to integrate.

§ 01 — How it works

Eight layers. One rule:
never cross a boundary.

If a layer crosses responsibility boundaries, the architecture is considered broken — and the system is built to fail rather than produce an untrustworthy result. Each layer has exactly one job and one output type.

Maxwell · Truss Platformstatic compiler-grade analysis · zero runtime instrumentation
Invar Engine01–03, 06
01Parserast.Module∅ semantic interpretation, type inference
02Type ExtractorTypeInfo(agent_vars, agent_calls)∅ heuristic inference, emitting violations
03Semantic AnnotatorList[Annotation]∅ violations, CFG analysis, mutate ast
06Semantic IR BuilderDict[fn → FunctionSemanticIR]∅ pattern matching, heuristic inference
Axiom Engine04–05, 07
04CFG BuilderCFG(nodes, edges, entry, exit)∅ semantic rules, dominance computation
05Dominance AnalyzerDominanceTree(dominators)∅ heuristics, semantics
07Invariant EvaluatorList[Violation]∅ AST/CFG mutation
Verity08
08Violation AdapterList[AdaptedViolation]∅ analysis logic, re-evaluation
ProvenanceVerifiable audit artefact for auditors, regulators, and insurers. Chain of custody, end to end.

§ 02 — Invariant library

17 active rules.
6 dimensions.

Every agent architectural failure mode, named and formalised. Due-diligence before you install.

IDDimensionInvariantTierRegulatory
AG-001GuardrailsLLM calls are wrapped (error containment)Tier SArt. 9, 15 · Art. 25(1) · DE-3
AG-002GuardrailsInfinite loop must have exit conditionTier SArt. 15 · Art. 25(1) · GV-2
AG-003Data ProvenanceNo hardcoded secrets in codebaseTier SArt. 9
AG-004GuardrailsNetwork/LLM calls require explicit timeoutTier SArt. 15 · Art. 25(2) · DE-3
AG-005Decision BoundaryAgent outputs validated before useTier SArt. 15 [Accuracy and Robustness] · Pillar 3 [Operational Reliability & Testing] · Measure 2.1 [System Robustness]
AG-006ObservabilityAgent outputs are logged before useTier SArt. 12 · Art. 25(3)
AG-007GuardrailsError handlers are non-empty (no silent pass)Tier SArt. 9 · Art. 25(1)
AG-008Decision BoundaryEvery irreversible action has a declared ownerTier SArt. 14
AG-009Decision BoundaryHuman override exists for high-impact actionsTier SArt. 14 · GV-6
AG-011Decision BoundaryFallback path exists and is reachableTier SArt. 15 · Art. 25(2) · DE-3
AG-012ReplayabilityModel version is pinnedTier SArt. 9 · MS-1
AG-014ReplayabilityExternal inputs are snapshotted before agent actsTier SArt. 12
AG-017ObservabilityInput-output trace is completeTier SArt. 12 · Art. 25(3)
AG-020ObservabilityConfidence score participates in control flowTier SArt. 9, 15
AG-021GuardrailsFallback path is non-LLMTier SArt. 15
AG-032Data ProvenanceInput source is declaredTier SArt. 9, 12
AG-036PolicyExplicit policy exists in execution pathTier SArt. 9, 14

Showing 17 of 17 active rules · 49 total invariants planned

AG-005Rule definition — YAML format
id: AG-005
dimension: Decision Boundary
semantic: Agent outputs must be validated before use
severity: CRITICAL
message: "Decision made on agent output without validation."
applies_to: decision_sinks
rule: dominated_by_validation == true
tags: [safety, accuracy, robustness]
 
# Multi-Framework Alignment Mapping
eu_ai_act_article: "Art. 15 [Accuracy and Robustness]"
dora_pillar: "Pillar 3 [Operational Reliability & Testing]"
nist_framework: "Measure 2.1 [System Robustness]"
iso_iec_42001: "ISO/IEC 42001 [AI System Integrity]"
us_executive_order: "Executive Order 14110 [AI Risk Management]"

§ 03 — Integration

Code-first.
Three paths in.

Install once. Run everywhere — local dev, CI/CD pipeline, or IDE. No agents at runtime, no instrumentation, no vendor lock-in.

CLI · Docker
Docker · CLI
Pull and run against any Python codebase. Provenance written to .maxwell/provenances/
$ docker pull ghcr.io/cernent/maxwell:0.4.1
$ docker run --rm -v $(pwd):/src \
ghcr.io/cernent/maxwell verify /src
→ provenance written to .maxwell/
CI/CD · GitHub
GitHub Action
One-liner PR check. Maxwell runs on every push, blocks merge on CRITICAL violations.
# .github/workflows/maxwell.yml
uses: cernent/maxwell-action@v1
with:
framework: langchain
fail-on: CRITICAL
IDE — coming 2026
IDE Extension
Inline invariant warnings as you write. Highlights structural gaps before you commit.