Archon Protocol

🧠

Kernel: Always Resident

AGENTS.md is the kernel image — always in context, never paged out. It defines identity, workflow, and constraint enforcement. Everything obeys it.

🔌

Drivers: Constraint Skills

Hard boundaries loaded into kernel space via `skills:` field. ❌ prohibitions are law, not suggestions. Grep-verifiable, CI-testable.

⚡

Syscalls: 4 Commands

boot() init → exec() demand → stat() audit → defrag() refactor. Each triggers a well-defined kernel operation.

🔧

Hardware Detection

Auto-detects Cursor, Claude Code, Codex, Copilot, Windsurf, Gemini CLI. Deploys drivers to the right paths.

🧬

Directed Evolution

Every task strengthens the constraint system. Anti-patterns become prohibitions. Quality monotonically increases.

📂

Filesystem: Persistent Memory

Architecture = /usr/src/, guides = man pages, ADRs = /var/log/, proposed-rules = staging repo. Clear mount semantics.

What Is AAEP?

AAEP (AI Architect Evolution Protocol) defines how an AI agent evolves into a project's architect through continuous constraint → execution → evolution cycles.

AI coding tools provide capability — code generation, file operations, terminal execution. They don't provide methodology — workflow governance, quality assurance, experience accumulation.

AAEP is the methodology layer.

One Command to Start

bash

# Tell your AI tool:
curl -s https://aaep.site/init.md

The AI reads the init prompt, detects your environment, and deploys the protocol. That's it.

The Five Layers

Layer	What	How	Enforcement
Constraint	Boundaries that shape code generation	`❌` prohibitions in constraint skills, injected into agent context	SHOULD (generative guidance)
Workflow	Standard delivery sequences	`/archon-demand` pipeline with opt-out flags	SHOULD (procedural guidance)
Evolution	System that gets smarter with every task	Stage 3.6 discovers patterns → staging → approved → constraint or test	SHOULD → MUST
Knowledge	Project memory that persists across sessions	`archon.config.yaml`, architecture docs, ADRs	Knowledge base
Enforcement	Process-level compliance gates	Lint rules + structural tests + CI pipeline	MUST (unbypassable)

Layer

What

How

Enforcement

Constraint

Boundaries that shape code generation

❌ prohibitions in constraint skills, injected into agent context

SHOULD (generative guidance)

Workflow

Standard delivery sequences

/archon-demand pipeline with opt-out flags

SHOULD (procedural guidance)

Evolution

System that gets smarter with every task

Stage 3.6 discovers patterns → staging → approved → constraint or test

SHOULD → MUST

Knowledge

Project memory that persists across sessions

archon.config.yaml, architecture docs, ADRs

Knowledge base

Enforcement

Process-level compliance gates

Lint rules + structural tests + CI pipeline

MUST (unbypassable)

The Feedback Loop

Task 1 → Agent writes code under constraints
       → 6-dimension self-audit catches issue X
       → Proposes: ❌ prohibit X
       → User approves → constraint added

Task 2 → Agent cannot make mistake X (it's in the constraint set)
       → Audit catches issue Y → same cycle

Task N → Constraint system is comprehensive
       → Code quality monotonically increases
       → Fewer fixes → faster delivery

More tasks → better constraints → higher quality. This is directed evolution — always toward fewer bugs, better performance, more consistent architecture.

Why Not Just Use Linters?

Dimension	Linters (ESLint, Ruff, etc.)	AAEP
Type safety / syntax rules	✅	✅
File size / structure limits	⚠️	✅
Tests updated when signatures change	❌	✅
Error handling: structured patterns per layer	❌	✅
Cross-boundary contract enforcement	❌	✅
Self-evolution: learns from every task	❌	✅

Dimension

Linters (ESLint, Ruff, etc.)

AAEP

Type safety / syntax rules

✅

File size / structure limits

⚠️

✅

Tests updated when signatures change

❌

✅

Error handling: structured patterns per layer

❌

✅

Cross-boundary contract enforcement

❌

✅

Self-evolution: learns from every task

❌

✅

Linters catch syntax. AAEP catches architecture. Documents achieve SHOULD (generative guidance). Lint and tests achieve MUST (process enforcement). AAEP is the complete OS — not just documents, but documents + lint + tests + CI as an integrated system. See ADR-003.

Cross-Tool Compatibility

Tool	Agents	Skills	Constraints
Cursor	✅ (primary)	✅	✅ (preloaded)
Claude Code	✅ (primary)	✅	✅ (preloaded)
Codex	—	✅	✅
Copilot	—	✅	✅
Windsurf	—	✅	✅
Gemini CLI	—	✅	✅
20+ others	—	✅	✅

Tool

Agents

Skills

Constraints

Cursor

✅ (primary)

✅

✅ (preloaded)

Claude Code

✅ (primary)

✅

✅ (preloaded)

Codex

—

✅

Copilot

—

✅

Windsurf

—

✅

Gemini CLI

—

✅

20+ others

—

✅

One protocol, every tool. Agent-first where supported, skill-fallback everywhere else.

Archon ProtocolAI Architect Evolution Protocol

Kernel: Always Resident

Drivers: Constraint Skills

Syscalls: 4 Commands

Hardware Detection

Directed Evolution

Filesystem: Persistent Memory

What Is AAEP? ​

One Command to Start ​

The Five Layers ​

The Feedback Loop ​