Features

​

Power Features

• 🌳 Git Worktrees - Run AI agents in parallel on isolated branches. Create worktree sub-agents from the git branch menu, each operating in their own directory. Work interactively in the main repo while sub-agents process tasks independently - then create PRs with one click. True parallel development without conflicts.
• 🤖 Auto Run & Playbooks - File-system-based task runner that processes markdown checklists through AI agents. Create Playbooks (collections of Auto Run documents) for repeatable workflows, run in loops, and track progress with full history. Each task gets its own AI session for clean conversation context.
• 🏪 Playbook Exchange - Browse and import community-contributed playbooks directly into your Auto Run folder. Categories, search, and one-click import get you started with proven workflows for security audits, code reviews, documentation, and more.
• 🎵 Maestro Symphony - Contribute to open source by donating AI tokens. Browse registered projects, select GitHub issues, and let Maestro clone, process Auto Run docs, and create PRs automatically. Distributed computing for AI-assisted development. (Encore Feature - on by default; toggle in Settings > Encore Features)
• 💬 Group Chat - Delegate the moderating. You appoint one agent as moderator and hand it the question; it routes to the right agents, follows up when an answer is thin, and keeps going for as many rounds as it takes before returning a synthesis. The multi-turn collaboration is the point, and it is what an inline @mention cannot do.
• 📣 Cross-Agent Mentions - Type @another-agent in any chat to consult it inline. Maestro forwards the relevant slice of your conversation, runs the other agent in the background without blocking you, and streams its reply back attributed to who answered. Pick a group from the @ picker to fan out to every member at once. Each mention is a single-turn consult and you stay the moderator, so reach for Group Chat when you want an agent to run the follow-ups instead.
• 🌐 Remote Control - Built-in web server with QR code access. Monitor and control all your agents from your phone. Supports local network access and remote tunneling via Cloudflare for access from anywhere.
• 🔗 SSH Remote Execution - Run AI agents on remote hosts via SSH. Leverage powerful cloud VMs, access tools not installed locally, or work with projects requiring specific environments - all while controlling everything from your local Maestro instance.
• 💻 Command Line Interface - Full CLI (maestro-cli) for headless operation. List agents/groups, run playbooks, manage settings and agent configs - all from the command line. Settings changes take effect instantly in the running app.
• 🚀 Multi-Agent Management - Run unlimited agents in parallel. Each agent has its own workspace, conversation history, and isolated context.
• 📬 Message Queueing - Queue messages while AI is busy; they’re sent automatically when the agent becomes ready. Edit, copy, hold/resume, reorder, or remove anything still waiting. Never lose a thought.
• 🛡️ Agent Resilience - Providers fail; your turn does not have to. When a turn dies on 529 Overloaded or a spent plan quota, Maestro resends the exact prompt on its own - backing off in seconds for a blip, or waiting for the real reset time it reads out of the error. One live status card in the transcript replaces the wall of error dialogs, and Auto Run batches resume themselves.
• 🔐 Global Environment Variables - Configure environment variables once in Settings and they apply to all agent processes and terminal sessions. Perfect for API keys, proxy settings, and tool paths.

​

Core Features

• 🔄 Dual-Mode Sessions - Each agent has both an AI Terminal and Command Terminal. Switch seamlessly between AI conversation and shell commands with Cmd+J / Ctrl+J.
• ❗ Command Mode - Press ! in an empty chat composer and it becomes a command line. git pull, ls, npm test run in the agent’s working directory (or on its SSH remote) and stream their output into the transcript, even while the agent is mid-turn. Full Tab completion over files, directories, git branches and tags, and your prior commands; Esc on an empty line hands the composer back to the agent.
• ⌨️ Keyboard-First Design - Full keyboard control with customizable shortcuts and mastery tracking that rewards you for leveling up. Cmd+K / Ctrl+K quick actions, rapid agent switching, and focus management designed for flow state.
• 📋 Session Discovery - Automatically discovers and imports existing sessions from all supported providers, including conversations from before Maestro was installed. Browse, search, star, rename, and resume any session.
• 🔀 Git Integration - Automatic repo detection, branch display, diff viewer, commit logs, and git-aware file completion. Pull, push, switch branches, and open PRs from the header branch pill or by right-clicking an agent, with live command output. Work with git without leaving the app.
• 📁 File Explorer - Browse project files with syntax highlighting, markdown preview, image viewing, and CSV/TSV tables. Reference files in prompts with @ mentions.
• ✏️ Image Annotator - Mark up screenshots before sending them. Freehand strokes, rectangles, ellipses, arrows, and inline text labels with pressure-aware perfect-freehand rendering, plus a crop tool that keeps your annotations editable instead of flattening them. Save in place, copy to clipboard, or annotate Auto Run attachments directly.
• 🎧 Media Player - Audio and video play in a small floating player you can drag anywhere, not a tab. Queue, playback speed, per-file resume, and a recently-played menu to jump back to anything you heard earlier. Keeps playing while you switch tabs and agents.
• 🕸️ Document Graph - Visualize markdown file relationships and wiki-link connections in an interactive graph. Navigate with keyboard shortcuts, adjust depth, and see how your documentation connects.
• 🗃️ File Formats - Maestro opens Parquet, JSON/JSONL, CSV/TSV, Markdown, Mermaid, HTML, images, and media each in a viewer built for it, several with their own filtering language. One page maps what opens as what, and what you can type at it.
• 🧮 Parquet Preview - Parquet files open as a live, filterable table with a schema rail. A typed query language (ts >= now-7d and price > 100) runs against the whole file, and Maestro skips the row groups it can prove cannot match - so a multi-gigabyte file filters instantly and never loads into memory.
• 📑 CSV and TSV Tables - Delimited files open as a sortable, searchable table instead of raw text. Double-click any row to flip it into a vertical field/value view that wraps long and multi-line values, with its own filter and arrow-key navigation between rows.
• 🔍 Powerful Output Filtering - Search and filter AI output with include/exclude modes, regex support, and per-response local filters.
• 🗂️ Cross-Tab Message Search - Search message history across every open tab in an agent at once with Opt+Cmd+F / Alt+Ctrl+F. Results are grouped by tab with previews; pick one to jump straight to that message, highlighted in place.
• ⚡ Slash Commands - Extensible command system with autocomplete. Create custom commands with template variables for your workflows. Includes bundled Spec-Kit for feature specifications and OpenSpec for change proposals.
• 💾 Draft Auto-Save - Never lose work. Drafts are automatically saved and restored per session.
• 🏷️ Automatic Tab Naming - Tabs are automatically named based on your first message. No more “New Session” clutter - each tab gets a descriptive, relevant name.
• 🪟 Tab Tiling - Split the Main Panel so several tabs are on screen at once: a chat above a terminal, a file beside the browser. Drag a tab onto an edge to tile it, or run Tile New AI Chat / Browser / File / Terminal Below from Quick Actions to create and place it in one step (Ctrl+Cmd+T / B / F / J do it directly). Resize with the dividers, move focus with Ctrl+Cmd arrows, and break the set apart whenever you want.
• 😴 Snooze Tabs - Hide a tab until later and get it back with a notification you have to dismiss. Works on any tab, and on a whole tiled group. Say when in plain language (2 weeks, next friday 3pm, aug 5) or pick from a calendar, attach a note-to-self that becomes the reminder, and on an AI tab a prompt the agent runs the instant it returns. Park work you can’t act on yet without closing it.
• 🔔 Custom Notifications - Execute any command when agents complete tasks, perfect for audio alerts, logging, or integration with your notification stack.
• 🎨 Beautiful Themes - 18 built-in themes across dark (Dracula, Monokai, Nord, Tokyo Night, Catppuccin Mocha, Gruvbox Dark), light (GitHub, Solarized, One Light, Gruvbox Light, Catppuccin Latte, Ayu Light), and vibe (Pedurple, Maestro’s Choice, Dre Synth, Winamp) categories, plus a fully customizable theme builder.
• ⏱️ WakaTime Integration - Automatic time tracking via WakaTime with optional per-file write activity tracking across all supported agents.
• 💰 Cost Tracking - Real-time token usage and cost tracking per session and globally.
• 📊 Usage Dashboard - Comprehensive analytics for tracking AI usage patterns. View aggregated statistics, compare agent performance, analyze activity heatmaps, and export data to CSV. Access via Opt+Cmd+U / Alt+Ctrl+U. (Encore Feature - on by default; toggle in Settings > Encore Features)
• 🎬 Director’s Notes - Bird’s-eye view of all agent activity in a unified timeline. Aggregate history from every agent, search and filter entries, and generate AI-powered synopses of recent work. Access via Cmd+Shift+O / Ctrl+Shift+O. (Encore Feature - on by default; toggle in Settings > Encore Features)
• 🎼 Concerto - Let agents compose live native views instead of walls of text: Movement panels on a resizable Concerto stage, plus always-on-top Cadenza HUD cards. Access via Opt+C / Alt+C. (Encore Feature - enable in Settings > Encore Features)
• 🏆 Achievements - Level up from Apprentice to Titan of the Baton based on cumulative Auto Run time. 11 conductor-themed ranks to unlock.
• 💬 Conversational Feedback - Submit bug reports and feature requests through an AI-guided conversation. The agent asks clarifying questions, runs read-only diagnostics on your machine so you do not have to gather them yourself, checks for duplicate issues, and creates a well-structured GitHub issue - no forms to fill out.

Note: Maestro currently supports Claude Code, Codex (OpenAI), and OpenCode as fully-integrated providers, plus Factory Droid, Copilot-CLI, Hermes (Nous Research), Pi, Qwen3 Coder, and Oh My Pi in beta. Support for additional providers (Gemini CLI) is planned for future releases based on community demand.