Krzysztof kuhy Rudnicki a456314f1a Add local-LLM setup script (ollama-cuda + qwen3 + Open WebUI) ... setup_local_llm.sh: idempotent Bash installer for a self-hosted local LLM stack tuned for the RTX 3090 (24GB) — installs ollama-cuda, writes a systemd drop-in enabling flash attention + Q8_0 KV-cache quantisation, pulls the model, creates a custom Ollama model with a developer system prompt, and launches Open WebUI via Docker. Verification: bash -n and shellcheck -x clean (see evidence artifact). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017RRCdR4D8SaVrN2xraMQxM		2026-07-11 00:16:24 +02:00
..
contracts	Harden phone_focus_mode CPU use; whitelist wake_alarm_sync	2026-07-11 00:16:11 +02:00
evidence	Add local-LLM setup script (ollama-cuda + qwen3 + Open WebUI)	2026-07-11 00:16:24 +02:00
memory	style(prettier): apply markdown/json formatting updates	2026-05-07 22:08:00 +02:00
plans	feat(phone-focus): add recovery workflow, automation scripts, and docs	2026-05-01 19:07:27 +02:00
sessions	chore(agent): add governance checks and artifact workflow scaffolding	2026-05-07 22:03:43 +02:00
specs	feat(phone-focus): add recovery workflow, automation scripts, and docs	2026-05-01 19:07:27 +02:00
workflows	chore(agent): add governance checks and artifact workflow scaffolding	2026-05-07 22:03:43 +02:00