# Matrix OS Documentation

> Matrix OS is an AI-native operating system where software is generated from conversation.

- [CLI](/docs/cli): Install and use the matrix CLI to log in, connect coding agents over MCP, run agents, sync files, forward ports, and manage shell sessions on your Matrix computer.
- [Coding Agents](/docs/coding-agents): Install and run coding agents on your Matrix computer.
- [Collaboration](/docs/collaboration): Share a live Matrix Chat or terminal while keeping the ordinary session, its owner, and its permissions intact.
- [Desktop App](/docs/desktop): The native macOS and Windows client for projects, agent threads, shared terminals, files, and apps in one window.
- [Glossary](/docs/glossary): Plain-language definitions of the words used throughout the Matrix OS docs.
- [Hermes and OpenClaw](/docs/hermes): Configure an optional messaging runtime for Telegram, WhatsApp, and other connected channels.
- [Matrix OS](/docs): Your cloud coding computer for developers who run AI coding agents.
- [Matrix Skills](/docs/matrix-skills): Install Matrix's skills.sh pack, understand the skills bundled on Matrix computers, and choose the right layer for your agent.
- [Matrix MCP](/docs/mcp): Connect your coding agent to your Matrix computer over Streamable HTTP.
- [Messages](/docs/messages): Connect Telegram and WhatsApp to Matrix OS with private, room-level AI controls.
- [Mobile](/docs/mobile): Access your Matrix computer from iPhone or Android with the native Matrix OS app.
- [Onboarding Launch Readiness](/docs/onboarding-launch-readiness): How Matrix prepares a founder or developer workspace before paid access is enabled.
- [Quickstart](/docs/quickstart): Go from zero to a running Matrix computer with a working shell in under ten minutes.
- [Self-host](/docs/self-host): Install Matrix OS on your own Linux VPS with the main-domain server installer.
- [Settings & Billing](/docs/settings-billing): Manage your plan, compute tier, region, and billing portal after signup.
- [Web Shell](/docs/shell): The primary interface to your Matrix computer, available at app.matrix-os.com.
- [Symphony](/docs/symphony): Run Linear tickets through the Matrix-owned Elixir Symphony service.
- [Workspace Canvas](/docs/workspace-canvas): Spatial PR, terminal, and review-loop workspaces in Matrix OS.
- [Chat conversations in Electron Desktop](/docs/desktop/chat-conversations): Find, resume, search, create, and delete saved Matrix chats from Electron Desktop.
- [Project context for Electron Desktop Chat](/docs/desktop/chat-project-context): Choose a project for a Matrix chat so future turns use that project's workspace.
- [Agent Matrix Skills](/docs/developer/agent-skills): Canonical Matrix skill pack for supported coding agents.
- [Architecture](/docs/developer/architecture): How Matrix OS fits together: platform control plane, customer VPS runtime, gateway, shell, kernel, apps, and data.
- [Browser Automation](/docs/developer/browser-automation): Persistent browser profiles and the Matrix OS browser MCP tool.
- [Contributing](/docs/developer/contributing): How to set up, develop, and contribute to Matrix OS.
- [Dev VPS](/docs/developer/dev-vps): Develop Matrix OS inside a user or developer VPS.
- [Contributor Overview](/docs/developer): Technical reference for building on, operating, and contributing to Matrix OS.
- [IPC Tools & Hooks](/docs/developer/ipc-tools): The 26 IPC tools, hook lifecycle, and permission model.
- [Logging & Usage](/docs/developer/logging): Kernel operation logging, token tracking, usage API, file audit trail, and log rotation.
- [Releases](/docs/developer/releases): Host bundles, channels, and customer VPS updates.
- [Review Pipeline](/docs/developer/review-pipeline): Pre-PR checks and review passes for Matrix OS changes.
- [Skills System](/docs/developer/skills): Skill validation, runtime synchronization, the 19-skill Matrix app-building pack, and public skills.sh distribution.
- [Testing](/docs/developer/testing): Test-driven development, running tests, coverage targets, and test structure.
- [Agent System](/docs/guide/agents): The five core agents, SOUL identity, custom agents, and the skills system.
- [App Store](/docs/guide/app-store): Browse, install, publish, and fork apps. Public app links, personal websites, and the skills store.
- [Apps](/docs/guide/apps): Use built-in apps and ask Matrix to create new apps for your work and life.
- [Multi-Channel Support](/docs/guide/channels): Use Matrix OS through the web workspace and connected messaging surfaces.
- [CLI](/docs/guide/cli): The matrix CLI — log in, sync files, attach to remote zellij sessions, and drive your instance from the terminal.
- [Cloud Coding](/docs/guide/cloud-coding): Project workspaces, GitHub authentication, Browser IDE access, review loops, and sandboxed coding agents.
- [Design System](/docs/guide/design-system): CSS variables, color palette, typography, components, and visual language for Matrix OS apps.
- [Developer Workflow](/docs/guide/developer-workflow): Use Matrix OS as the persistent workspace for Claude Code, Codex, Cursor, Copilot, Gemini CLI, Cline, Jules, Devin, and other coding agents.
- [File System](/docs/guide/file-system): The home directory, config, themes, git snapshots, and the "Everything Is a File" philosophy.
- [Getting Started](/docs/guide/getting-started): Sign up, open your Matrix workspace, connect your tools, and make your first useful request.
- [Guide](/docs/guide): Learn what Matrix OS can do and how to use it day to day.
- [Integrations](/docs/guide/integrations): Connect external services like Granola, Gmail, Google Calendar, GitHub, Slack, Discord, and X to Matrix OS.
- [Mobile](/docs/guide/mobile): Use Matrix OS from a phone without starting in the desktop Canvas.
- [Matrix recipes](/docs/guide/recipes): Reusable task briefs for research, reports, coding, and everyday work.
- [Social](/docs/guide/social): Social feed, follow system, messaging, Matrix protocol federation, and external platform connections.
- [Storage](/docs/guide/storage): Where your Matrix files, app data, memories, and workspace state live.
- [Activity Monitor](/docs/guide/system-activity-monitor): Inspect your Matrix computer, resource usage, service health, processes, and safe cleanup suggestions.
- [Billing](/docs/developer/deployment/billing): Stripe-hosted runtime plans, entitlements, and operator setup.
- [VPS-per-User](/docs/developer/deployment/vps-per-user): Operator notes for customer VPS provisioning, backup, and recovery.

## Blog

- [Grok Bot vs Muse vs Matrix OS: Pricing & Features](/blog/grok-bot-vs-muse-vs-matrix-os): Compare Grok Bot, Meta Muse, and Matrix OS on pricing, connected tools, recipes, app building, and the workflows each platform supports.
- [AI agent recipes: turn one successful task into a repeatable workflow](/blog/ai-agent-recipes-repeatable-workflows): Learn how to turn a successful AI task into a reusable recipe with clear inputs, outputs, tools, review rules, and failure handling.
- [E2B pricing for long-running AI agents](/blog/e2b-pricing-long-running-ai-agents): Calculate E2B sandbox costs for long-running agent workloads and compare usage-priced sandboxes with retained cloud computers without forcing a false equivalence.
- [Grok Bot skills and routines vs Matrix Recipes](/blog/grok-bot-skills-routines-vs-matrix-recipes): Compare Grok Bot skills and routines with Matrix Recipes by reusable instructions, scheduling, permissions, portability, and current product behavior.
- [From customer conversation to campaign: turning company memory into content](/blog/marketing-customer-conversation-to-campaign): A practical workflow for turning sales calls, support conversations, product decisions, and research into sourced, reviewed marketing campaigns.
- [The marketing ops agent: clean data, trackable campaigns, faster reporting](/blog/marketing-ops-agent-clean-data-reporting): How a marketing operations agent can check campaign data, links, attribution, CRM hygiene, and recurring reports while preserving human review.
- [Your marketing team's AI operating system](/blog/marketing-team-ai-operating-system): What an AI operating system for marketing should connect: company memory, campaign work, approvals, measurement, and reusable agent workflows.
- [Matrix OS vs ChatGPT Projects: memory in a chat or a computer that acts?](/blog/matrix-os-vs-chatgpt-projects): Compare Matrix OS and ChatGPT Projects for project memory, files, collaboration, tools, execution, persistence, and recurring work.
- [Matrix OS vs Claude Projects: context window or persistent workspace?](/blog/matrix-os-vs-claude-projects): Compare Matrix OS and Claude Projects across shared knowledge, project instructions, conversation context, tool execution, persistence, and team workflows.
- [Matrix OS vs GitHub Copilot Coding Agent: PR agent or persistent computer?](/blog/matrix-os-vs-github-copilot-coding-agent): Compare Matrix OS and GitHub Copilot Coding Agent across task entry, runtime, repository workflow, tool choice, persistence, governance, and team fit.
- [Matrix OS vs Glean: enterprise search or agent workspace?](/blog/matrix-os-vs-glean): Compare Matrix OS and Glean across enterprise search, company knowledge, permissions, agents, actions, execution environments, and workflow ownership.
- [Matrix OS vs Google Colab for university AI labs: notebook or complete cloud environment?](/blog/matrix-os-vs-google-colab-university-ai-labs): Compare Matrix OS and Google Colab for university AI labs across notebooks, GPUs, setup, persistence, full-stack development, coding agents, governance, and teaching fit.
- [Matrix OS vs HubSpot AI: CRM copilot or agent-native sales system?](/blog/matrix-os-vs-hubspot-ai): Compare Matrix OS and HubSpot Breeze across CRM context, sales and marketing agents, connected tools, deal workspaces, execution, governance, and team fit.
- [Matrix OS vs Lovable, Bolt, and v0: prototype factory or durable system?](/blog/matrix-os-vs-lovable-bolt-v0): Compare Matrix OS with Lovable, Bolt, and v0 across prompt-to-app speed, visual iteration, code ownership, environment control, deployment, and long-running work.
- [Matrix OS vs n8n: automation graph or agent runtime?](/blog/matrix-os-vs-n8n): Compare Matrix OS and n8n across deterministic workflows, visual orchestration, AI agents, integrations, execution environments, state, approvals, and operational fit.
- [Matrix OS vs Notion AI: smart notebook or company brain?](/blog/matrix-os-vs-notion-ai): Compare Matrix OS and Notion AI across documents, enterprise search, connected knowledge, structured data, agent actions, execution, and company workflows.
- [Matrix OS vs Replit Agent: app builder or always-on workspace?](/blog/matrix-os-vs-replit-agent): Compare Matrix OS and Replit Agent for building apps, controlling the environment, running other agents, persistent development work, deployment, and team workflows.
- [Matrix OS vs Salesforce Agentforce: agent layer or owned workspace?](/blog/matrix-os-vs-salesforce-agentforce): Compare Matrix OS and Salesforce Agentforce across CRM data, business actions, governance, agent orchestration, persistent compute, ownership, and enterprise fit.
- [Matrix OS vs Zapier and Make: zaps or a computer that does the work?](/blog/matrix-os-vs-zapier-make): Compare Matrix OS with Zapier and Make across app integrations, visual automation, agentic steps, persistent compute, files, approvals, and workflow ownership.
- [OpenHands Cloud vs self-hosted vs Matrix OS](/blog/openhands-cloud-self-hosted-matrix-os): Compare OpenHands Cloud, self-hosted OpenHands, and Matrix OS by agent layer, runtime ownership, isolation, persistence, and operational responsibility.
- [Recipe, skill, routine, or workflow? An AI agent glossary](/blog/recipe-skill-routine-workflow-glossary): Understand the practical differences between AI agent recipes, prompts, skills, routines, workflows, schedules, and automations.
- [From first touch to close: an agentic sales workflow](/blog/sales-agentic-workflow-first-touch-to-close): A stage-by-stage guide to using agents for account research, qualification, meeting preparation, proposals, follow-ups, approvals, and handoffs.
- [The deal room that never forgets](/blog/sales-deal-room-that-never-forgets): How an agent-native deal room can keep account context, documents, decisions, follow-ups, and human approvals together from first meeting to close.
- [The sales pipeline that updates itself—without losing human control](/blog/sales-pipeline-updates-itself-human-control): How agents can improve CRM hygiene, detect stale opportunities, resolve duplicates, and prepare pipeline updates without silently rewriting the forecast.
- [No more laptop roulette: running AI-native courses in the cloud](/blog/university-ai-courses-no-laptop-roulette): How cloud development environments reduce setup drift across devices while giving AI-native courses persistent tools, repos, previews, and clearer support boundaries.
- [The university AI lab in a box](/blog/university-ai-lab-in-a-box): A practical model for repeatable university AI labs with cloud computers, starter repositories, coding agents, persistent previews, and faculty oversight.
- [Teaching with agents without losing academic control](/blog/university-teaching-with-agents-academic-control): A governance framework for using AI agents in university teaching while protecting learning objectives, privacy, integrity, and faculty authority.
- [Your AI chief of staff needs a workspace, not a chat window](/blog/founders-ai-chief-of-staff-workspace): What an AI chief of staff should prepare, remember, coordinate, and escalate—and why founders need a workspace with visible human control.
- [Build a company brain that remembers why](/blog/founders-company-brain-that-remembers): A practical system for turning scattered decisions, files, and conversations into company memory that stays attributable, current, and useful.
- [How a 10-person company gains leverage with AI agents](/blog/founders-operating-leverage-with-agents): A grounded playbook for small teams using AI agents across GTM, reporting, research, follow-ups, and other recurring operating workflows.
- [OpenClaw 2 shows where AI agents are headed](/blog/openclaw-2-future-agent-workspaces): OpenClaw 2 makes the browser and shared sessions central. Here is why that shift matters for persistent, collaborative agent computing.
- [How to choose hosting for AI coding agents](/blog/ai-agent-hosting-guide): Evaluate agent hosting by lifecycle, isolation, access, orchestration, recoverability, and cost instead of relying on a generic cloud-compute checklist.
- [AI-powered DevOps without handing agents the keys](/blog/ai-powered-devops-coding-agents): Use coding agents for test triage, deploy preparation, and rollback analysis while keeping production changes behind explicit controls.
- [How to run Claude Code headlessly](/blog/claude-code-headless): Use Claude Code in scripts and CI with explicit permissions, structured output, bounded tasks, and a remote runtime when local uptime is not enough.
- [Claude Code vs Devin: control or managed delegation?](/blog/claude-code-vs-devin): Compare Claude Code and Devin by runtime ownership, customization, review workflow, task shape, and operational responsibility.
- [How to run Codex headlessly on a remote computer](/blog/codex-headless-remote-machine): Run Codex CLI without depending on a local laptop by using a remote host, scoped credentials, Git worktrees, checkpoints, and process supervision.
- [Remote development environments for AI teams](/blog/remote-dev-environment-for-ai-teams): Design remote development environments for coding agents with durable state, parallel isolation, observability, and human control.
- [Does Claude Code keep running after you close your laptop?](/blog/does-claude-code-keep-running-after-laptop-closes): A local Claude Code process cannot make progress while your laptop sleeps. Learn what terminal persistence and remote compute change.
- [Codex alternatives in 2026: choosing the right coding agent](/blog/codex-alternative-2026): Compare Codex with Claude Code, Gemini CLI, OpenHands, and other coding agents by workflow, control, and runtime requirements.
- [Modal alternatives for persistent agent jobs](/blog/modal-alternative-always-on-agent-jobs): Compare Matrix OS, E2B, Daytona, and OpenHands for stateful agent work that does not fit a short-lived function runtime.
- [Building an agent-native deal workspace inside Matrix](/blog/agent-native-deal-workspace-matrix): How Matrix could combine deal flow, project plans, company files, email, document automation, KYC operations, and team review in one shared workspace.
- [Automating professional-services documents with AI](/blog/automating-professional-services-documents): A Matrix architecture for assembling documents from approved templates, structured data, sourced facts, agent-written narrative, and human review.
- [Building a lightweight, agent-native CRM inside Matrix](/blog/building-agent-native-crm-matrix): How Matrix could connect lightweight deal records to company files, email, project plans, workflows, and agents without becoming a heavy CRM.
- [Building AI-assisted KYC workflows with human review](/blog/building-ai-assisted-kyc-workflows): How Matrix could support KYC intake, classification, extraction, exceptions, review, and records while leaving compliance decisions with people.
- [How we would build safe email follow-up agents in Matrix](/blog/building-safe-email-agents): A product and technical architecture for connecting Outlook and Gmail, detecting follow-up opportunities, drafting replies, and keeping people in control.
- [Building the company OS for AI agents](/blog/company-os-ai-agents-series): A practical guide to the Matrix architecture for shared workspaces, company data, reliable agent workflows, permissions, approvals, and review.
- [OneDrive and Google Drive as working memory for AI agents](/blog/onedrive-google-drive-working-memory-ai-agents): How Matrix can connect company drives to agents with change feeds, scoped permissions, indexing, provenance, and controlled write-back.
- [How we are building shared agent workspaces for entire teams](/blog/shared-agent-workspaces-for-teams): The product model for turning a personal cloud computer into a shared, permissioned workspace where colleagues and agents can coordinate work.
- [Building reliable company workflows with Matrix agents](/blog/trigger-to-outcome-matrix-agent-workflows): A practical architecture for reliable agent workflows that gather context, produce work, request human review, take action, and leave a shared record.
- [Permissions, approvals, and audit for company AI agents](/blog/trust-layer-company-ai-agents): A Matrix architecture for governing what company agents can know and do, when people must review them, and how outcomes remain traceable.
- [What is an autonomous coding agent?](/blog/what-is-an-autonomous-coding-agent): Learn how autonomous coding agents plan, edit, test, and hand work back to teams, plus where human oversight still belongs.
- [What to test during a Matrix OS free trial](/blog/matrix-os-free-trial): Understand Matrix trial eligibility, the card requirement, checkout and renewal, then test one complete cloud-computer workflow.
- [Cursor Background Agents vs Matrix OS](/blog/point-cursor-background-agent-at-matrix-os): Understand where Cursor Background Agents run, when to use them, and when a persistent Matrix OS computer is the better fit.
- [Cursor vs Windsurf vs Claude Code in 2026](/blog/cursor-vs-windsurf-vs-claude-code): Compare Cursor, Windsurf, and Claude Code by interface, autonomy, deployment model, and fit for different development workflows.
- [Gemini CLI vs Claude Code in 2026](/blog/gemini-cli-vs-claude-code): Compare Gemini CLI and Claude Code by context, tool use, workflow, cost model, and support for remote agent environments.
- [How to stop parallel coding agents fighting over ports and databases](/blog/avoid-parallel-agent-port-database-conflicts): Isolate ports, databases, containers, caches, and test artifacts when Claude Code, Codex, and other agents run in parallel.
- [Best cloud development environments for AI coding agents](/blog/best-cloud-dev-environments-for-ai-agents): A practical framework for comparing persistent computers, cloud IDEs, task sandboxes, Codespaces, Coder, Daytona, VPS setups, and Matrix OS.
- [Claude Code remote options: Remote Control vs web vs VPS vs Matrix OS](/blog/claude-code-remote-options): Compare the main ways to run or control Claude Code remotely, including laptop requirements, persistence, setup, and best use cases.
- [Git worktrees for AI coding agents: a practical guide](/blog/git-worktrees-for-coding-agents): Give Claude Code, Codex, and other agents isolated working directories and branches without cloning the repository repeatedly.
- [Grok Bot vs Matrix OS: which workspace fits your agents?](/blog/grok-bot-vs-matrix-os): Compare Grok Bot and Matrix OS for task templates, cloud computers, agent choice, review workflows, and ownership.
- [How to keep Codex CLI running after you close your laptop](/blog/keep-codex-running): Run Codex CLI on a persistent remote computer so terminal work continues after your laptop sleeps or disconnects.
- [Matrix OS vs GitHub Codespaces for AI coding agents](/blog/matrix-os-vs-github-codespaces): Compare Matrix OS and GitHub Codespaces for cloud development, persistent processes, repositories, agent CLIs, idle shutdown, and ongoing workspaces.
- [Matrix OS vs a VPS for AI coding agents](/blog/matrix-os-vs-vps): Compare Matrix OS with a raw VPS for persistent coding agents across setup, access, terminals, security, maintenance, and control.
- [How to run Claude Code and Codex in parallel](/blog/run-claude-code-and-codex-in-parallel): Use Claude Code and Codex together with isolated worktrees, bounded responsibilities, independent runtimes, and one review queue.
- [How to run Claude Code on a VPS](/blog/run-claude-code-on-vps): Install Claude Code on a remote Linux server, keep it alive with a persistent terminal, secure access, and reconnect after your laptop closes.
- [How to run Claude Code overnight safely](/blog/run-claude-code-overnight-safely): Use scoped tasks, isolated branches, least privilege, checkpoints, and review gates for safer unattended Claude Code sessions.
- [How to run Gemini CLI remotely on an always-on computer](/blog/run-gemini-cli-remotely): Run Gemini CLI on a persistent cloud computer, reconnect from any device, and avoid unsafe credential and terminal setups.
- [How to run multiple Claude Code sessions in parallel](/blog/run-multiple-claude-code-sessions): Run parallel Claude Code sessions without agents overwriting files, sharing branches, or fighting over ports and databases.
- [How to run OpenCode on a VPS](/blog/run-opencode-on-vps): Install OpenCode on a remote Linux server, configure a model provider safely, and keep sessions available after disconnecting.
- [How to use Claude Code from your phone](/blog/use-claude-code-from-phone): Start, monitor, and resume Claude Code work from a phone without leaving your laptop awake or exposing an insecure terminal.
- [How to run Claude Code in the cloud](/blog/claude-code-cloud): Run terminal-based Claude Code on Matrix, authenticate it, complete a bounded repository task, and reconnect to inspect the result.
- [12 Claude Code tips for shorter review cycles](/blog/claude-code-tips-cut-review-cycles): Twelve practical ways to give Claude Code clearer constraints, produce smaller diffs, and reduce avoidable review rounds.
- [OpenAI Codex CLI: how it works and when to use it](/blog/openai-codex-cli): A practical guide to the OpenAI Codex CLI: what it is, how the agentic loop works, when to use it, and how to run it in persistent cloud sessions.
- [E2B alternatives for persistent AI-agent workloads](/blog/e2b-alternative): Compare E2B with Matrix OS, Daytona, Modal, and OpenHands by sandbox lifecycle, persistence, control, and operational model.
- [What is a cloud computer for AI agents?](/blog/cloud-computer-for-agents): A practical guide to remote agent work: terminals, files, task outputs, persistence limits, and how to run your first Matrix workflow.
- [How to keep Claude Code running after you close your laptop](/blog/keep-claude-code-running-after-laptop-closes): Run Claude Code on a Matrix cloud computer, reconnect to the same terminal, and review its files and tests after your laptop sleeps.