backend-agent d7e007a4ea docs: rework LLM adapter section to use local CPU-only models via Ollama ...

Replace cloud-based LLM providers (Anthropic/OpenAI) with a local Ollama
sidecar running lightweight quantized models (qwen2.5-coder:1.5b as primary,
phi3:mini as fallback). All generation stays under 60s on CPU, data never
leaves the network, and there are zero API costs.

Updated: architecture diagram, component description, technology choices,
project layout, docker-compose, env vars, and consequences sections.

2026-05-08 07:17:58 +00:00

..

adr-001.md

docs: rework LLM adapter section to use local CPU-only models via Ollama

2026-05-08 07:17:58 +00:00