Files

Ezra 1b3bca9902 Implement Archon Architecture POC (Epic #370 , Dispatch #371 )

Three-layer architecture implementation:
- Layer 1: Thin Hermes profile (profile.yaml, < 50 lines)
- Layer 2: Claw Code runtime (harness.py, tool_registry.py)
- Layer 3: Gemma via Ollama (ollama_client.py)

Features:
- Tool registry with pattern matching (/time, /status, /echo, /ollama_list)
- Full routing between tool execution and intelligence layer
- Ollama client with streaming and chat support
- Comprehensive integration test suite (12 tests)
- Connection to localhost:11434 using gemma3:4b model

2026-04-02 19:47:00 +00:00

3.0 KiB

Raw Blame History

Archon Architecture Proof-of-Concept

A three-layer architecture separating identity, runtime logic, and intelligence.

Architecture Overview

┌─────────────────────────────────────────────────────────────┐
│  Layer 1: Hermes Profile (Thin)                              │
│  - Identity & routing only                                   │
│  - No intelligence or reasoning logic                        │
│  - Pure configuration (< 50 lines)                           │
└─────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────┐
│  Layer 2: Claw Code Runtime                                  │
│  - All business logic lives here                             │
│  - Tool registry and execution                               │
│  - Message routing and orchestration                         │
└─────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────┐
│  Layer 3: Gemma 4 via Ollama                                 │
│  - The actual intelligence                                   │
│  - Local inference at localhost:11434                        │
│  - Model: gemma3:4b (available) / gemma4:4b (target)         │
└─────────────────────────────────────────────────────────────┘

Files

File	Purpose
`profile.yaml`	Thin Hermes layer - identity only
`runtime/harness.py`	Claw Code runtime stub
`runtime/tool_registry.py`	Tool definitions and registry
`ollama_client.py`	Gemma 4 interface layer
`test_integration.py`	End-to-end integration test

Quick Start

# Run integration test
python3 test_integration.py

# Test Ollama connection
python3 ollama_client.py "Hello, Gemma!"

Design Principles

Profile is THIN - Only identity, no logic
Runtime owns everything - All intelligence orchestration
Local inference - No external API dependencies
Testable - Full integration test coverage

Epic Reference

Implements Epic #370: Archon Architecture Dispatch #371: Proof-of-Concept Implementation

3.0 KiB Raw Blame History