# Persistent Memory

## System
- 3 agents configured: opencode, Hermes Agent, Gemini CLI
- Dashboard runs on FastAPI (Python) — localhost only
- All skills follow _template/ convention
- Memory consolidation: 2026-07-17 (run — all files clean, stale truncated run log from 2026-06-29 cleaned)

## User
- Name: User
- Budget: Strictly free tiers

## Active Work
- Building Agentic OS from scratch (May 17, 2026)
- Kitchen-Inventory — catering kitchen management system (on antigravity)
- Pendleton-comms-live — walkie talkie app for catering events (on Railway)

## Technology Preferences
- Preferred model: deepseek-v4-flash-free
- Free tiers: GCP Free, GitHub Student Dev Pack, Colab, Kaggle
- Knowledge management via markdown vaults

## Consolidated Insights (2026-06-29)
- **opencode** times out on non-code tasks (brainstorming, tdd-cycle, backup-skill, code-review, goal-planner, test-plugin) — route these to hermes
- **hermes** can also time out on complex multi-step tasks — keep queries short
- **daily-standup** is the most-run skill; hermes executes faster than opencode for it
- **Score tracking**: all 18 skills have empty score-history.json — no eval data yet
- **All learnings files** are concise (under 200 words each), no compression needed
- **No contradictions** found across skill learnings
- **recent-decisions.md**: 3 entries archived (all from 2026-05-17), 0 recent — no archiving needed