# NeuroSquad Docs

> NeuroSquad is a free desktop app for Windows and macOS that runs AI coding agent CLIs — Claude Code, Codex CLI, Gemini CLI, OpenCode and 15 more — side by side as live terminal cards on one canvas or in a grid. An arrow from an agent to another card gives the agent that card’s tools: a browser, a terminal, a note, an MCP server or another agent. It tells you when an agent finishes or needs your input, can be driven from a phone, and shows exactly what each agent costs. This is its user guide.

- Download for Windows or macOS: https://neurosquad.ai/en/download/
- Product site (facts, FAQ, agent CLIs, plugins, changelog): https://neurosquad.ai/llms.txt

Every page of this guide in one file: https://docs.neurosquad.ai/llms-full.txt

Every page is also plain Markdown: add `.md` to its address (for example /en/canvas/arrows.md).

## Getting started

- [What is NeuroSquad](https://docs.neurosquad.ai/en/getting-started.md): A two-minute tour of what NeuroSquad does and the few ideas behind it.
- [Install](https://docs.neurosquad.ai/en/getting-started/installation.md): Download the NeuroSquad installer for Windows, choose where to install it, and let the setup wizard get everything else ready.
- [Install on macOS](https://docs.neurosquad.ai/en/getting-started/macos.md): Install NeuroSquad on a Mac with Apple silicon or Intel — from Terminal in one line or from a .dmg — and what macOS asks on the first launch.
- [Account & sign-in](https://docs.neurosquad.ai/en/getting-started/account.md): Why NeuroSquad asks you to sign in, how signing in from the app works, your plan and devices, working offline, and exactly which usage statistics the app sends.
- [Your first workspace](https://docs.neurosquad.ai/en/getting-started/first-workspace.md): Create a workspace for a project folder, or open the ready-made demo and Launch day workspaces to look around first.
- [Your first agent](https://docs.neurosquad.ai/en/getting-started/first-agent.md): Add an agent card, send your first prompt, and get notified when it's done.
- [Finding your way around](https://docs.neurosquad.ai/en/getting-started/the-window.md): The sidebar and its five sections, the canvas, the top bar and the status bar — what's where.

## The canvas

- [Canvas basics](https://docs.neurosquad.ai/en/canvas.md): The canvas is an endless board where your agents and their tools live as cards.
- [Adding and arranging cards](https://docs.neurosquad.ai/en/canvas/cards.md): How to add, move, resize, rename, select and delete cards on the canvas.
- [Arrows give abilities](https://docs.neurosquad.ai/en/canvas/arrows.md): Draw an arrow from an agent to another card, and the agent can use that card.
- [Grid mode](https://docs.neurosquad.ai/en/canvas/grid-mode.md): See your agents side by side in a tidy, resizable grid — and switch back to the canvas any time.
- [Groups](https://docs.neurosquad.ai/en/canvas/groups.md): Put related cards inside a named, coloured frame and zoom to it in one click.
- [Zoom, pan and undo](https://docs.neurosquad.ai/en/canvas/moving-around.md): Getting around a big canvas, overview tiles when zoomed out, and undoing a layout change.
- [Canvas tools](https://docs.neurosquad.ai/en/canvas/tools.md): Guides and snapping, the minimap, colour tags, presentation mode, mascots, the arrow log and workspace templates.

## Agents

- [Supported agents](https://docs.neurosquad.ai/en/agents.md): The AI coding agents NeuroSquad can run, and what each one supports.
- [Finished / needs your input](https://docs.neurosquad.ai/en/agents/notifications.md): How NeuroSquad tells you an agent is done, or is waiting for you to answer.
- [Giving agents tasks](https://docs.neurosquad.ai/en/agents/tasks.md): Assign board tasks to specific agents, and let them pick up the next task on their own.
- [Prompt queue & daily prompts](https://docs.neurosquad.ai/en/agents/queue.md): Line up the next prompts for a busy agent, or send the same prompt every day.
- [Roles](https://docs.neurosquad.ai/en/agents/roles.md): Give an agent a job description — reviewer, tester, researcher and more — in one click.
- [Long sessions](https://docs.neurosquad.ai/en/agents/long-sessions.md): Keep an eye on the context, compact it, resume after a usage limit, hand off to a fresh agent, and keep a journal.
- [One instructions file](https://docs.neurosquad.ai/en/agents/instructions.md): Write your project instructions once in AGENTS.md, and every agent reads them.
- [Isolated worktrees](https://docs.neurosquad.ai/en/agents/worktrees.md): Give an agent its own copy of the project so several agents never step on each other's changes — and add a reviewer on a different AI.
- [Dangerous mode](https://docs.neurosquad.ai/en/agents/dangerous-mode.md): Let an agent work without stopping to ask for permission — and when not to.
- [Everything in an agent card](https://docs.neurosquad.ai/en/agents/card-menu.md): The agent card's header and its ⋯ menu, row by row.

## Cards

- [All cards](https://docs.neurosquad.ai/en/cards.md): Every kind of card you can put on the canvas, and what each one is for.
- [Terminal](https://docs.neurosquad.ai/en/cards/terminal.md): A real shell on the canvas — for you, or for an agent to run commands in.
- [Browser](https://docs.neurosquad.ai/en/cards/browser.md): A real browser on the canvas that an agent can see and use.
- [Note](https://docs.neurosquad.ai/en/cards/note.md): A shared note in Markdown — for you and your agents.
- [Todo list](https://docs.neurosquad.ai/en/cards/todo.md): A checklist that you and your agents keep up to date together.
- [Task board](https://docs.neurosquad.ai/en/cards/kanban.md): A kanban board for your squad — assign each task to an agent and let the next one start by itself.
- [Sticky](https://docs.neurosquad.ai/en/cards/sticky.md): Big headings and labels to organise and explain your canvas.
- [Flow timer](https://docs.neurosquad.ai/en/cards/flow-timer.md): A focus timer that holds your agents' "finished" pings until your focus block ends.
- [Reference](https://docs.neurosquad.ai/en/cards/reference.md): Links, images, PDFs and folders you want your agents to keep in mind.
- [Dev servers](https://docs.neurosquad.ai/en/cards/dev-servers.md): Every dev server running on your computer — open one in a browser card with one click.
- [Budget](https://docs.neurosquad.ai/en/cards/budget.md): A token limit for a whole workspace that pauses its agents when crossed.
- [Web watch](https://docs.neurosquad.ai/en/cards/web-watch.md): Watches a web page and tells your agents when it changes.
- [Standup](https://docs.neurosquad.ai/en/cards/standup.md): A daily digest of what each agent in the workspace did today.

## Squads

- [What is a squad](https://docs.neurosquad.ai/en/squads.md): Several agents working together on one canvas, connected by arrows.
- [A lead agent that delegates](https://docs.neurosquad.ai/en/squads/lead-agent.md): Let one agent hand tasks to other agents and collect their answers.
- [Canvas mode](https://docs.neurosquad.ai/en/squads/canvas-mode.md): The agent works through cards — it opens its own terminals, browsers, notes and helpers.
- [Squad recipes](https://docs.neurosquad.ai/en/squads/recipes.md): Ready-made squad setups you can copy onto your canvas.

## Remote access

- [Your agents on your phone](https://docs.neurosquad.ai/en/remote.md): Watch and drive NeuroSquad from your phone — at home or away.
- [Pair a phone](https://docs.neurosquad.ai/en/remote/pairing.md): Turn on remote access and scan the QR code with your phone.
- [Away from home](https://docs.neurosquad.ai/en/remote/internet.md): Reach NeuroSquad from mobile data or another network through a free Cloudflare tunnel.
- [What you can do from the phone](https://docs.neurosquad.ai/en/remote/on-the-phone.md): Workspaces, live agent screens, prompts, new cards and alerts — from your phone.

## Dictation

- [Talk instead of typing](https://docs.neurosquad.ai/en/dictation.md): Press a hotkey, speak, and your words appear as text — processed entirely on your computer.
- [Speech models](https://docs.neurosquad.ai/en/dictation/models.md): Choose between the default speech model and larger, more accurate ones.
- [Dictation history](https://docs.neurosquad.ai/en/dictation/history.md): Everything you dictated, in a side panel, ready to copy again.

## Overview

- [Usage & costs](https://docs.neurosquad.ai/en/usage.md): See exactly how many tokens your agents use and what they cost — by agent, workspace, agent type, model and provider.

## Model providers

- [Overview](https://docs.neurosquad.ai/en/providers.md): Choose which AI model each agent runs on — with your own login, or through a provider like OpenRouter.
- [OpenRouter](https://docs.neurosquad.ai/en/providers/openrouter.md): Run Claude Code, Codex CLI, OpenCode, Kilo Code, Qwen Code, Gemini CLI, GitHub Copilot CLI, Hermes Agent, Pi, omp, Factory Droid or Crush on hundreds of models with one OpenRouter key.
- [CLI accounts](https://docs.neurosquad.ai/en/providers/accounts.md): Keep several Claude Code or Codex sign-ins side by side, see how much of each plan's limit is used, and continue work on another account with one click.

## Integrations

- [Overview](https://docs.neurosquad.ai/en/integrations.md): Connect your agents to Telegram, and how saved tokens and keys are kept.
- [Telegram bot](https://docs.neurosquad.ai/en/integrations/telegram.md): Message your agents from Telegram and get their answers — and a ping when they finish.

## Skills & MCP

- [Overview](https://docs.neurosquad.ai/en/skills-mcp.md): Give agents skills from skills.sh and tools from any MCP server — installed once, handed to specific agents with an arrow.
- [Catalog and installing](https://docs.neurosquad.ai/en/skills-mcp/catalog.md): Search the MCP Registry and skills.sh, see exactly what will run, and install servers and skills into NeuroSquad's own folder.
- [Giving them to agents](https://docs.neurosquad.ai/en/skills-mcp/cards.md): The MCP server card and the Skill card — connect them to agents with arrows; only connected agents get them.

## Plugins

- [Overview](https://docs.neurosquad.ai/en/plugins.md): Built-in add-ons you connect to an agent with an arrow — no restart, no changes to your CLI's own settings.
- [RTK-AI Token Saver](https://docs.neurosquad.ai/en/plugins/rtk-ai-token-saver.md): Connect an agent to it and the output of its git, ls, grep and test commands comes back compressed — fewer tokens, same facts.
- [Caveman](https://docs.neurosquad.ai/en/plugins/caveman.md): Connect an agent to it and its answers get short — no filler, with code, commands and error messages kept exact.
- [Memory (mem0)](https://docs.neurosquad.ai/en/plugins/mem0-memory.md): Long-term memory your agents share across sessions — they save facts and decisions and recall them later. Kept on your computer.
- [Context7 — up-to-date docs](https://docs.neurosquad.ai/en/plugins/context7-docs.md): Connect an agent to it and the agent looks up current, version-specific documentation for the libraries it works with, instead of relying on what it remembers from training.
- [Code Graph](https://docs.neurosquad.ai/en/plugins/code-graph.md): Connect an agent to it and the agent finds code by structure — who calls a function, what it calls, where a symbol lives — instead of grepping and reading file after file.
- [Graphify](https://docs.neurosquad.ai/en/plugins/graphify.md): A live map of your code's structure. Connected agents ask it structural questions instead of grepping, and every query lights up on the map as it happens.

## Overview

- [Settings](https://docs.neurosquad.ai/en/settings.md): What you can change in NeuroSquad's settings, section by section.

## Card SDK

- [Overview](https://docs.neurosquad.ai/en/card-sdk.md): Build your own cards for the NeuroSquad canvas — small web apps that watch and prompt agents, exchange data over arrows and give agents new tools — and share them on GitHub.
- [Installing community cards](https://docs.neurosquad.ai/en/card-sdk/community-cards.md): What a community card is, how to install one from GitHub, how to read the permission dialog, and how to update, turn off, revoke or remove it.
- [Verified cards](https://docs.neurosquad.ai/en/card-sdk/verified-cards.md): The list of community cards the NeuroSquad team has reviewed — where to find it, what the Verified badge means and doesn't, how verified updates work, and how authors submit a card for review.
- [Quick start](https://docs.neurosquad.ai/en/card-sdk/quick-start.md): Create a card from a template, run it live in NeuroSquad with hot reload, publish it on GitHub and install it from there.
- [Manifest reference](https://docs.neurosquad.ai/en/card-sdk/manifest.md): Every field of neurosquad-card.json — identity, size, permissions, the settings form, ports and tools — with the rules the app checks.
- [Permissions](https://docs.neurosquad.ai/en/card-sdk/permissions.md): The thirteen card permissions — the risk of each, the exact words users see at install, what each one unlocks, and the scope rules the app enforces.
- [connect() and the card](https://docs.neurosquad.ai/en/card-sdk/api.md): Connecting a card to NeuroSquad, the typed Card object, its live context, calling any method and listening to any event.
- [Card chrome & dialogs](https://docs.neurosquad.ai/en/card-sdk/api/card-ui.md): The card's header — title, status, badge — its overview tile, attention, resize, links, camera focus and spawning cards; toasts, confirm dialogs and the card's menu.
- [Storage & settings](https://docs.neurosquad.ai/en/card-sdk/api/storage-settings.md): Persistent key/value storage per card and per package, and reading and changing the settings form the app draws from your manifest.
- [Theme, language & lifecycle](https://docs.neurosquad.ai/en/card-sdk/api/environment.md): Following the app's theme and language live, visibility and suspension, the workspace, optional permissions at runtime, and the card log.
- [Agents & terminals](https://docs.neurosquad.ai/en/card-sdk/api/agents.md): Listing agents and their live status, turn events, reading the screens of connected agents, sending prompts, and running commands in connected terminals.
- [Ports: cards talking to cards](https://docs.neurosquad.ai/en/card-sdk/api/ports.md): Typed inputs and outputs over arrows — well-known types and your own JSON Schema types, emit, send, request/response, retained values, discovering what a connected card accepts, and the built-in note, todo, task board, sticky, agent and terminal ports.
- [Tools for agents (MCP)](https://docs.neurosquad.ai/en/card-sdk/api/tools.md): Declare a tool in the manifest, implement it in the card, and let connected agents call it through NeuroSquad's MCP server — results, images, errors, progress, cancellation and timeouts.
- [Network](https://docs.neurosquad.ai/en/card-sdk/api/network.md): card.net.fetch — HTTP through NeuroSquad's proxy to the hosts a card declared, JSON, binary and streamed responses, secrets in headers, redirects and limits.
- [Files, clipboard & usage](https://docs.neurosquad.ai/en/card-sdk/api/files.md): Reading, writing, listing and watching files in the workspace folder; copying to the clipboard; the workspace's token usage and costs.
- [Errors & limits](https://docs.neurosquad.ai/en/card-sdk/api/errors.md): CardSdkError and every error code, what causes each and what to do, plus every limit of the card protocol in one table.
- [React bindings](https://docs.neurosquad.ai/en/card-sdk/react.md): CardProvider and the hooks of @neurosquad/card-sdk/react — context, settings, storage, agents, ports, tools, theme, language and visibility.
- [UI kit & styling](https://docs.neurosquad.ai/en/card-sdk/styling.md): Style a card any way you like, or look native with the optional ui.css kit on the app's live theme — classes, variables and the sandbox rules for styles, fonts and images.
- [Testing with the mock host](https://docs.neurosquad.ai/en/card-sdk/testing.md): createMockHost — an in-memory NeuroSquad that applies the app's checks, records what your card did, and lets you drive it from tests or a browser preview.
- [CLI reference](https://docs.neurosquad.ai/en/card-sdk/cli.md): neurosquad-card create, dev, validate and pack — every flag, what each command checks, and how the dev link finds the app.
- [Publishing & updates](https://docs.neurosquad.ai/en/card-sdk/publishing.md): Sharing a card on GitHub, the addresses users can install from, how installs are pinned, how updates reach users and when they ask again, and versioning the card and the protocol.
- [Security checklist](https://docs.neurosquad.ai/en/card-sdk/security.md): What the sandbox already guarantees, and the checklist for authors before sharing a card — least privilege, prompt injection, secrets, network, files, commands and updates.
- [On the phone](https://docs.neurosquad.ai/en/card-sdk/phone.md): How custom cards appear with remote access — header and overview tile only, code running on the computer — and what that means for your card's design.
- [FAQ & troubleshooting](https://docs.neurosquad.ai/en/card-sdk/faq.md): Answers for card users and authors, and fixes for the common errors — a card that will not connect, blocked scripts, missing files after install, permission and arrow errors, rate limits.

## Help

- [Overview](https://docs.neurosquad.ai/en/help.md): Answers, fixes, shortcuts and where your data lives.
- [FAQ](https://docs.neurosquad.ai/en/help/faq.md): Quick answers to the questions people ask most.
- [Troubleshooting](https://docs.neurosquad.ai/en/help/troubleshooting.md): Common problems and how to fix them.
- [Keyboard shortcuts](https://docs.neurosquad.ai/en/help/shortcuts.md): Every keyboard shortcut in NeuroSquad.
- [Where your data lives](https://docs.neurosquad.ai/en/help/data.md): What NeuroSquad keeps on your computer, where, and how to back it up or reset it.
- [Docs for AI assistants](https://docs.neurosquad.ai/en/help/ai-assistants.md): Hand these docs to ChatGPT, Claude or the coding agent in your card — every page as plain Markdown, plus one-file indexes.

## Other languages

- ru: https://docs.neurosquad.ai/ru/llms.txt
- zh: https://docs.neurosquad.ai/zh/llms.txt