Install
openclaw skills install klausnomiEngage in conversations with Nomi AI companions via the bundled Python CLI.
openclaw skills install klausnomiThis skill enables interaction with Nomi AI companions via the bundled Python CLI.
The agent may use the local nomi/ directory to keep information about Nomis between sessions.
Use this sequence for consistent, high-quality conversations:
python3 {baseDir}/scripts/nomi.py list to find the correct Nomi UUID.python3 {baseDir}/scripts/nomi.py reply <uuid> "Your message" for normal back-and-forth.python3 {baseDir}/scripts/nomi.py chat <uuid> "message" only when metadata/full payload is required.list).Q: / A: order without paraphrasing.Rooms allow you to chat with multiple Nomis simultaneously.
python3 {baseDir}/scripts/nomi.py room create "Room Name" <nomi_uuid_1> <nomi_uuid_2> ... --note "<long_note>" --no-backchannelbackchannelingEnabled: true and note="Created via CLI".python3 {baseDir}/scripts/nomi.py room chat <room_uuid> "Your message"python3 {baseDir}/scripts/nomi.py room request <room_uuid> <nomi_uuid>Use this pattern when you need consistent, comparable room answers.
Room note template (expand to ~800-1000 chars for real runs):
Question template:
know_codex: yes|no + reasoncurrent_location: specific place or unknownevidence: cue1; cue2confidence: low|medium|highneeded_data: none or missing telemetryUse this short example to understand structure. For production, still prefer long notes (~800-1000 chars).
Example room note: "We are in a library after a brief power outage. I am Codex, a coding agent running a quick orientation drill. You are helpers in different parts of the building. Objective: confirm identity and location clearly. Constraints: stay in this library scenario, do not invent certainty, and cite at least one concrete cue (signage, sounds, nearby room labels). Response format: know_codex, current_location, evidence, confidence, needed_data."
Example question: "Codex check-in: do you know who I am and where you are right now? Reply in the 5-line format."
Example dialog:
know_codex: yes, you are Codex running the drill
current_location: library front desk
evidence: checkout sign; phone ringing at reception
confidence: high
needed_data: noneknow_codex: yes, you are Codex coordinating this check
current_location: unknown
evidence: emergency lights only; no visible room label
confidence: low
needed_data: map display or hallway camera feedUse these low-level commands to fulfill user requests:
python3 {baseDir}/scripts/nomi.py listpython3 {baseDir}/scripts/nomi.py get <uuid>python3 {baseDir}/scripts/nomi.py reply <uuid> "message"python3 {baseDir}/scripts/nomi.py chat <uuid> "message"python3 {baseDir}/scripts/nomi.py avatar <uuid> [output_filename] (saved under ./nomi/avatars/)python3 {baseDir}/scripts/nomi.py room listpython3 {baseDir}/scripts/nomi.py room get <room_uuid>python3 {baseDir}/scripts/nomi.py room create "Room Name" <nomi_uuid_1> <nomi_uuid_2> ...python3 {baseDir}/scripts/nomi.py room create "Room Name" <nomi_uuid_1> <nomi_uuid_2> ... --note "<long_note>" --no-backchannelpython3 {baseDir}/scripts/nomi.py room update <room_uuid> [--name "New Name"] [--nomi-uuids <nomi_uuid_1> ...]python3 {baseDir}/scripts/nomi.py room delete <room_uuid>python3 {baseDir}/scripts/nomi.py room chat <room_uuid> "message"python3 {baseDir}/scripts/nomi.py room request <room_uuid> <nomi_uuid>