adminandClaude
ec6fd7157a
Surveyed ~/dev (mewtwo) + jirachi. Battery mirrors actual workload:
mcp_server -> 9 MCP servers (joplin/obsidian/vault/project-rag/...)
tts_pipeline -> TTS/audio pipelines (Chatterbox, aygea-tts, vr-to-tts)
webhook_bridge -> Twitch/Discord bridges (multistream, notifier, overlay)
data_service -> data/API (Supabase MCP, PostgresHA, dashboard)
automation_glue -> batch/cron glue (fix-tokens, notesCleanup)
rust_service -> big Rust services (NineSentry, aystreamer): tokio
channels + Arc/Mutex + error enums + graceful shutdown
Each prompt is ~2-3KB (fits 128k context with output room), single-file,
runnable, graded on the same 5-pillar rubric. aygea_test_battery.md is the
index + scoring notes + the prompt_id schema the dashboard will need for
multi-prompt support.
Co-Authored-By: Claude <noreply@anthropic.com>
🧪 Local LLM Benchmark Suite
Grades local LLM models (run via LM Studio on an Apple M3 Max / 48 GB) on a strict systems-coding prompt — a pure-stdlib Python concurrent async LFU cache with TTL eviction and ACID transactions — and renders the results into a cyberpunk-terminal dashboard.
What's in here
prompts/
lfu_cache_prompt.txt # the exam prompt every model gets
grading.txt # the grader's rubric (5 pillars × 20 pts = 100)
outputs/ # raw model .py outputs (named <model>-<quant>.py)
data/
benchmark_history.json # persistent results store (source of truth)
generate_dashboard.py # reads the JSON → builds dashboard.html + pages/*.html
dashboard.html # generated — main leaderboard + charts (gitignored)
pages/ # generated — per-model detail pages (gitignored)
Workflow
-
Feed
prompts/lfu_cache_prompt.txtto a model in LM Studio. -
Save its output to
outputs/<model>-<quant>.py. -
Grade it (audit the 5 pillars, capture tok/sec + tokens + TTFT), and append its entry to
data/benchmark_history.json. Seeprompts/grading.txtfor the rubric. -
Regenerate the site:
python3 generate_dashboard.pyThis (re)writes
dashboard.htmland everypages/<model>.html.
Viewing locally
python3 -m http.server 8000
# open http://localhost:8000/dashboard.html
Deploying (Gitea + Coolify)
The repo holds source only (outputs/, data/, generate_dashboard.py, prompts/).
The generated dashboard.html and pages/ are gitignored — Coolify runs
python3 generate_dashboard.py as a build step, then serves the static files.
See DEPLOY.md for the exact Coolify service config.
Hardware
Apple M3 Max, 48 GB unified memory. Local inference via LM Studio. A cloud model (DeepSeek V4 Flash) is included as a quality baseline.