documentTOOLS.md4/3/2026, 9:15:22 PM

TOOLS.md - Local Notes

Skills define _how_ tools work. This file is for _your_ specifics — the stuff that's unique to your setup.

What Goes Here

Things like:

  • Camera names and locations
  • SSH hosts and aliases
  • Preferred voices for TTS
  • Speaker/room names
  • Device nicknames
  • Anything environment-specific

Examples

markdown

Cameras

  • living-room → Main area, 180° wide angle
  • front-door → Entrance, motion-triggered

SSH

  • home-server → 192.168.1.100, user: admin

TTS

  • Preferred voice: "Nova" (warm, slightly British)
  • Default speaker: Kitchen HomePod

Why Separate?

Skills are shared. Your setup is yours. Keeping them apart means you can update skills without losing your notes, and share skills without leaking your infrastructure.

---

Parallel Agent Platforms

  • Hermes Agent (isolated eval install)

- code: /root/.parallel-platforms/hermes-agent

- runtime home/config: /root/.parallel-platforms/hermes-home

- launcher: /root/.parallel-platforms/bin/hermes-isolated

- rule: use the isolated launcher, not a global hermes, unless Tim explicitly chooses to operationalize Hermes into the main stack

memU

  • local source checkout: /root/.openclaw/workspace/vendor/memU

  • isolated Python 3.13 runtime: /root/.openclaw/workspace/.tools/memu
  • default Python launcher on PATH: /root/.local/bin/memu-python
  • package version currently installed in that runtime: memu-py 1.5.1

Known caveats from local validation:

  • upstream memu-server console entrypoint in memu-py 1.5.1 is broken (ModuleNotFoundError: memu.server)
  • SQLite initialization is currently broken in this release on this host; in-memory service construction works
  • safest default is import-based usage via memu-python

Quick use:

bash

memu-python - <<'PY'

from memu import MemoryService

service = MemoryService(llm_profiles={"default": {"api_key": "..."}})

print(type(service).__name__)

PY

Add whatever helps you do your job. This is your cheat sheet.