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
6.9 KiB
6.9 KiB