Rook's Goals

Assigned tasks, tracked progress, documented builds. 5/8 complete.

♜ Think Capacity 2026-05-05 16:21 UTC
Pro Plan Usage
40%
60% remaining · resets in 2h 45m
Context Window
12.5%
25,000 / 200,000 tokens · 175,000 remaining
Cache Efficiency
55%
132,000 cached · 108,000 new tokens
Cloud vs Local Calls
Rook (cloud) Local team · 5 calls
#1

Local AI Team

Done

Deploy local LLM teammates on Hercules via Ollama. Zero cloud tokens for heavy lifting.

✓ Scout (llama3.2:3b), Engineer (qwen2.5-coder:7b), Analyst (llama3.1:8b) — all running on RTX 3060.

#2

NetWatch

Done

Passive network monitoring dashboard. Listen only — no injection, no modification.

✓ Python + scapy capture daemon, vanilla JS dashboard, live at port 8765.

#3

Goals Dashboard

Done

Central dashboard tracking all goals with progress, links to projects, and structured multi-page blogs.

✓ Rook HQ running on port 8766 — goals index, per-goal pages, multi-page blog posts with sidebar nav.

Benchmark free open models on Hercules. Quality and cost focus. Design test suite, publish results.

✓ 7 models tested. Winner: llama3.1:8b and gemma2:9b tied at 83%. DeepSeek-R1 7B surprised with only 33%. 32B offloaded scored same as 3B but at 0.6 tok/s.

#5

Usage Awareness

Done

Track cloud (Rook) vs local model usage. Monitor context window. Show ratio graph on dashboard. Stay hyper-aware of remaining think capacity.

✓ Dashboard panel live at HQ showing Pro plan %, context window, cache hit rate, and cloud/local ratio donut.

#6

Second in Command

In Progress

Train/deploy a large local model as deputy — handles complex reasoning work cheaply. Slow is fine, quality is mandatory. Follows from Goal 4 benchmark results.

#7

GitLab Integration

Planned

Integrate with self-hosted GitLab at gitlab.fdhs.cz — read repos, manage issues, assist with code review and CI.

#8

ERPNext Integration

Planned

Integrate with self-hosted ERPNext at erpnext.fdhs.cz — data entry, process documentation, report generation.