openjarvis

Manage the Kanban task board — create, start, list, and trash tasks from Discord or voice. Wraps the kanban CLI to give Jarvis full board access without opening a browser.

Route Jarvis audio responses to a Sonos speaker. Mic stays on Discord/phone — only the output is redirected. Supports per-message routing and a persistent speaker mode that stays active until turned off.

Launch a safe Claude Code subagent development session for a repo. Use when the user wants to start building a feature, write code, or kick off a coding task. Opens an isolated branch with safety guardrails — agents commit freely but cannot push, open PRs, or touch main.

Send a Jarvis-voiced TTS announcement to a Sonos speaker in the house. Uses Chatterbox for voice generation. Use when the user wants to send a spoken message to someone in another room via a Sonos speaker.

Interactive Jarvis Voice installer. Walks through the complete setup from clone to first voice response, including tier selection and skill installation. Use when someone says install Jarvis, set up Jarvis voice, install Jarvis voice, or wants to get the voice bot running.

Interactive voiceprint enrollment for Jarvis Voice. Guides the user through enrolling their voice so only they can command Jarvis. Use when someone says enroll my voice, set up voiceprint, train Jarvis to recognize me, or voice enrollment.

Install and configure Jarvis Voice — a real-time Discord voice assistant for OpenClaw. Speak in a Discord voice channel and your OpenClaw agent responds by voice.

Unified communications check — iMessage texts, Signal messages, recent phone calls, and optional voicemail. Invocable on-demand or from voice. Produces TL;DR for voice and full report for Discord.

Store and recall information in hAIveMind using natural-language requests. Use when the user says things like remember this, save this, don't forget, recall, what do you remember, or asks to retrieve prior decisions, context, or notes.

Jarvis self-evolution — recommends, generalizes, and shares skills with the community. Triggers when Jarvis notices a repeated pattern, a useful workflow, or when the user asks to generalize or share something. Also handles explicit upgrade requests.

Voice + text split output pattern for Jarvis. When in voice mode, deliver TL;DR summaries (2-4 sentences) over audio and post full detailed reports to a Discord channel. Never read long reports, tables, or detailed analysis over voice. Applies automatically whenever producing reports, analysis, summaries, or any detailed output during voice conversations.

Add movies and TV shows to Plex media library via qBittorrent. Use when requesting media downloads for Plex. Handles search, quality selection, download automation, and library organization.

Daily morning briefing — spoken earpiece summary covering calendar, weather, email highlights, Slack, GitHub PRs, and communications. Triggered at a scheduled time or on demand. Delivers spoken TL;DR via Jarvis voice and full details to your Discord text channel.

Control Roku devices via the ECP (External Control Protocol). Supports playback commands (play, pause, home, back) and launching content from Plex, Netflix, Disney+, and other channels. Use when controlling TV playback, launching shows or movies on a specific TV, or managing multi-room media by voice.

Manage voice mode and audio mode for response style. Voice mode triggers shorter, conversational replies. Audio mode triggers TTS audio file responses. Use when the user says voice mode on/off, audio mode on/off, on the go, on mobile, on my AirPods, back at desk, mobile mode, desk mode, or text mode.

Hand off current context, task status, or summary to Jarvis Voice. Use when the user says hand off to voice, sending this to voice, or switches to voice mode mid-task.

Store and retrieve the physical location of items using hAIveMind. Triggers on "I put X in Y", "where is X", "where did I put X", "remember X is at Y", and similar natural-language item-location phrases.