# Rumus ## Docs - [Invitation codes & rewards](https://www.rumus.ai/docs/account/invitations.md): Generate a code to invite a friend to Rumus, redeem one a friend gave you, and what the reward is. - [Sign up & sign in](https://www.rumus.ai/docs/account/sign-in.md): Create a Rumus account, sign in with GitHub or email, and what happens after. - [Config sync](https://www.rumus.ai/docs/account/sync.md): What syncs to the cloud (and what doesn't), how conflicts are handled, and where to find the controls. - [Vault & encryption](https://www.rumus.ai/docs/account/vault.md): Stronghold-backed end-to-end encryption for hosts, credentials, and other sensitive data — locked with a secret key only you hold. - [Vault sync & recovery](https://www.rumus.ai/docs/account/vault-sync.md): How encrypted vault data flows between your devices, and how to recover on a new install. - [Agentic execution](https://www.rumus.ai/docs/ai/agentic.md): How the AI agent runs commands, edits files, fetches URLs, and uses MCP tools to complete tasks end-to-end. - [Smart autocomplete](https://www.rumus.ai/docs/ai/autocomplete.md): Inline command suggestions that learn from your shell history and the current context. - [Command approval & whitelist](https://www.rumus.ai/docs/ai/command-approval.md): Decide which commands run automatically, which need confirmation, and which are blocked outright. - [Conversation management](https://www.rumus.ai/docs/ai/conversations.md): Auto-naming, automatic summarization, and task lists — how Rumus keeps your AI threads coherent over time. - [MCP integration](https://www.rumus.ai/docs/ai/mcp.md): Connect your own tools to the agent with the Model Context Protocol — databases, internal APIs, ticket systems, anything. - [AI assistant overview](https://www.rumus.ai/docs/ai/overview.md): What the agent does, how the sidebar is laid out, and where to find the rest of the AI features. - [Plan mode](https://www.rumus.ai/docs/ai/plan-mode.md): How the agent automatically drafts a checklist for multi-step jobs and works through it step by step. - [Rules & skills](https://www.rumus.ai/docs/ai/rules-skills.md): Teach the agent your conventions once with rules; give it reusable named procedures with skills. - [Sub-agents](https://www.rumus.ai/docs/ai/sub-agents.md): When the agent spawns independent workers in parallel — and how their results flow back into your conversation. - [Web search](https://www.rumus.ai/docs/ai/web-search.md): How the agent reaches out to the open web — local DuckDuckGo by default, or Rumus's cloud search API for better results. - [Fonts & ligatures](https://www.rumus.ai/docs/customization/fonts.md): Choose the terminal font, fallback, size, and line height — and turn on programming ligatures if your font supports them. - [Keyboard shortcuts](https://www.rumus.ai/docs/customization/keyboard.md): Bind every common action to whatever key feels natural — and find conflicts before they bite. - [Display language](https://www.rumus.ai/docs/customization/language.md): Switch the Rumus UI to your preferred language. - [Themes & color schemes](https://www.rumus.ai/docs/customization/themes.md): Pick the window theme, accent color, and terminal palette. - [Can Rumus See My Data?](https://www.rumus.ai/docs/faq/can-rumus-see-my-data.md): How Rumus keeps your data private — even from us. - [Core concepts](https://www.rumus.ai/docs/getting-started/core-concepts.md): A short tour of the building blocks that make Rumus work the way it does. - [Installation](https://www.rumus.ai/docs/getting-started/installation.md): Install Rumus on macOS, Windows, or Linux. - [Migrate from another terminal](https://www.rumus.ai/docs/getting-started/migrate.md): Bring your hosts, profiles, and habits over from iTerm2, Warp, Windows Terminal, and friends. - [Quickstart](https://www.rumus.ai/docs/getting-started/quickstart.md): Open Rumus, try the AI in a local terminal, then graduate to managing remote servers. - [Introduction](https://www.rumus.ai/docs/index.md): Rumus is an AI-native terminal that reimagines how developers work with servers. - [Anthropic](https://www.rumus.ai/docs/models/anthropic.md): Use your Anthropic API key to run Claude models inside Rumus. - [Built-in models](https://www.rumus.ai/docs/models/built-in.md): Models included with Rumus Pro, what each one costs, and how to track your usage. - [DeepSeek](https://www.rumus.ai/docs/models/deepseek.md): Use your DeepSeek API key with Rumus to run DeepSeek V3.2 and the V3.2 Reasoner. - [Google AI](https://www.rumus.ai/docs/models/google.md): Use your Google AI key to run Gemini Pro and Flash models in Rumus. - [Kimi (Moonshot AI)](https://www.rumus.ai/docs/models/kimi.md): Use your Moonshot AI API key with Rumus to run Kimi K2.5, K2 Thinking, and Moonshot V1. - [Ollama (local models)](https://www.rumus.ai/docs/models/ollama.md): Run open-weight models on your own machine and use them inside Rumus. - [OpenAI](https://www.rumus.ai/docs/models/openai.md): Use your OpenAI API key with Rumus to run GPT and o-series models. - [OpenAI-compatible endpoints](https://www.rumus.ai/docs/models/openai-compatible.md): Connect Rumus to OpenRouter, vLLM, LiteLLM, LocalAI, Azure OpenAI, or any service that speaks the OpenAI API. - [Overview](https://www.rumus.ai/docs/models/overview.md): Use Rumus's built-in models, bring your own API keys, or run local models — sometimes all at once. - [Z.AI](https://www.rumus.ai/docs/models/zai.md): Use your Z.AI key to run the GLM family in Rumus, including the Coding-specialized variant. - [Host groups & known_hosts](https://www.rumus.ai/docs/remote/groups-known-hosts.md): Organize hosts into nested groups, and manage the trust list of host keys Rumus has seen before. - [SSH host management](https://www.rumus.ai/docs/remote/hosts.md): Save SSH targets, configure auth, and connect — all from inside the encrypted vault. - [Jump host chains](https://www.rumus.ai/docs/remote/jump-hosts.md): Reach internal servers by chaining one or more bastion hosts. - [Resource monitoring](https://www.rumus.ai/docs/remote/monitoring.md): Live CPU, memory, disk, and GPU charts for any host — local or remote — as a workspace canvas card. - [Proxy settings](https://www.rumus.ai/docs/remote/proxy.md): Connect through HTTP, HTTPS, or SOCKS5 proxies — configured per host. - [SFTP file browser](https://www.rumus.ai/docs/remote/sftp.md): Browse, upload, download, and edit files on any saved SSH host. - [Workspace](https://www.rumus.ai/docs/terminal/canvas.md): Arrange multiple terminals, monitors, and notes on a zoomable canvas — and broadcast commands to several at once. - [Profiles](https://www.rumus.ai/docs/terminal/profiles.md): Define which shell, environment, and starting directory each new local terminal tab should use. - [Search](https://www.rumus.ai/docs/terminal/search.md): Find text in the scrollback of a terminal tab. - [Shell integration](https://www.rumus.ai/docs/terminal/shell-integration.md): Command decorations, working-directory tracking, and prompt detection — powered by OSC 133 markers. - [Tabs and windows](https://www.rumus.ai/docs/terminal/tabs.md): Open, organize, and manage tabs at the top of the Rumus window. ## Optional - [Website](https://www.rumus.ai) - [Community](https://www.rumus.ai/community)