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
26 lines
503 B
YAML
26 lines
503 B
YAML
name: Archon-POC
|
|
display_name: Archon (Proof-of-Concept)
|
|
model: gemma3:4b
|
|
variant: archon
|
|
provider: ollama
|
|
ollama_host: http://localhost:11434
|
|
|
|
creator: Ezra
|
|
lineage: Archon / Timmy Time Nexus
|
|
purpose: Three-layer architecture POC
|
|
|
|
# THIN PROFILE - No logic, only identity and routing
|
|
# All intelligence lives in Claw runtime + Gemma layer
|
|
|
|
routing:
|
|
runtime: claw.harness
|
|
intelligence: ollama.gemma
|
|
|
|
constraints:
|
|
max_tokens: 4096
|
|
temperature: 0.7
|
|
|
|
tagging:
|
|
required: true
|
|
tag: "#archon-poc"
|