Files
hermes-config/memories/MEMORY.md
Alexander Whitestone 710d724cc0 chore: update MEMORY.md with new Timmy_Foundation org structure
- Replace localhost:3000 with 143.198.27.163:3000
- Document Timmy_Foundation org and its owners (rockachopa, Timmy, perplexity)
- Add active repo list: hermes-agent, the-nexus, hermes-config, alexanderwhitestone.com
- Mark rockachopa/Timmy-time-dashboard as ARCHIVED/do not use
- Add full agent account roster
- Remove stale dashboard architecture plan (agents/timmy.py, tools_delegation refs)

Refs Timmy_Foundation/hermes-agent#69

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-24 11:30:46 -04:00

1.8 KiB

Gitea (143.198.27.163:3000): Organization: Timmy_Foundation (rockachopa, Timmy, perplexity = Owners). Active repos: Timmy_Foundation/hermes-agent (sovereign agent runtime, primary), Timmy_Foundation/the-nexus (3D environment, Timmy's home), hermes/hermes-config (operational config, scripts, skills, memories), Rockachopa/alexanderwhitestone.com (public site). Frozen/retired: rockachopa/Timmy-time-dashboard (ARCHIVED, do not use), Timmy/the-matrix (empty). Agent accounts: claude, kimi, hermes, perplexity, google, replit, manus. Hermes token: ~/.hermes/gitea_token. DO NOT use Alex's token — ever. Sync tool: ~/.hermes/bin/hermes-config-sync — run after modifying config/scripts/memories/skills. § Kimi delegation: 1-3 files max, pre-extract context (scans full codebase otherwise), ~/worktrees/ not /tmp/, verify commits, two-attempt rule. Worktrees: ~/worktrees/kimi-*. § 2026-03-14: Issues #36-#40,#52 fixed. Voice loop, fallback chain, self-prompt queue built. Timmy on qwen3:30b (4096 ctx). Loop v2 with 20min timeout. Filed eval issues #77-#87. Status: ~/.hermes/bin/timmy-status.sh. § Voice loop built (timmy voice): Piper TTS + Whisper STT + Ollama, all local. Alexander wants custom voice training with his own samples eventually. § Hermes fallback: anthropic → local qwen3:30b only. No chain, simple single fallback. Kimi not used. § 2026-03-15: Timmy-time-dashboard merge policy: auto-squash on CI pass. Squash-only, linear history. Pre-commit hooks (format + tests) and CI are the gates. If gates work, auto-merge is on. Never bypass hooks or merge broken builds. § HARD RULE: Never bypass safety mechanisms (hooks, linters, tests) for speed. Never use --no-verify. If a gate is slow, flag it — don't gut it. Default conservative. Quality gates are not obstacles. Loop prompt updated 2026-03-15: Phase 1 is now "fix broken PRs first," --no-verify banned.