Docs

Core River concepts, terminology, and product foundations.

Start Here#

• Welcome — What River is, why it's structured the way it is, and where to start.
• Quickstart — Get from zero to a working River workspace in five steps.
• Pricing & Plans — Plans, AI usage budgets, and how billing works.
• How River Works — The six layers that make River feel like an operating system, not an app.
• Spaces — The rooms you work in — persistent, contextual, and returnable.
• Groups — Folders for the modern world — they hold anything, nest infinitely, and know what's inside.
• Windows — What's open right now — your current working set on top of everything that's permanent.
• Entities — The things themselves — every doc, file, email, task, agent, and artifact in River.
• Event Stream — River's nervous system — every action, human or AI, recorded in real time.
• Search — The fastest way back — find any entity by title, content, or context.
• Activity — Your audit trail — what was created, edited, and produced, in human-readable form.
• Notifications — How River talks back to you when something matters.
• Dataspaces — The ownership boundary — your personal world model and your team's shared one.
• Overview — How AI is layered into River — reactive, scheduled, triggered, and ambient.
• SpaceChat — The AI sidebar in every Space — the fastest way to do anything in River.
• Edit, Plan & Ask — The three SpaceChat modes — and what each one guarantees.
• Tools & Commands — How AI acts on entities — the verbs every Agent and Workflow can use.
• Local Models — Run AI on your own hardware with Ollama — private, fast, and offline-capable.
• Agents — Reusable AI specialists that run on triggers, schedules, or demand — your autonomous workforce.
• Building an Agent — Create, configure, and deploy a River Agent in under five minutes.
• Triggers — When Agents run — events, schedules, and manual invocation.
• Skills — Focused, single-shot AI capabilities — the specialized moves the AI uses inside larger tasks.
• Workflows — Deterministic visual graphs for processes that must run the same way every time.
• Node Types — Every built-in Workflow node — triggers, data, River-native, and human/LLM-in-the-loop.
• Schedules — Recurring automations — like cron jobs, but first-class entities.
• Jobs — Every autonomous run, recorded — queued, running, succeeded, or failed.
• Apps — Purpose-built environments for specific kinds of work — all sharing the same entity system and AI.
• Mail — Email with AI-powered triage, smart folders, one-click composition, and multi-account support.
• Tasks — Task management with AI extraction, smart views, and keyboard shortcuts.
• Notes — Fast capture and long-form notes — always in the entity system, always reasonable-over by AI.
• Pages — Rich document editing — multiplayer, AI-native, designed for the things people read.
• Docs — Reference documents, knowledge bases, and the long memory of your team.
• Sheets — Spreadsheets with formulas, live data, and AI inside every cell.
• Contacts — Your relationship graph — people, companies, and the connections between them.
• Browser — In-workspace web browsing — research, clip, summarize, and save to entities.
• Image Studio — AI image generation and editing with cloud and local providers.
• Video Studio — An AI video pipeline — ingest, analyze, edit, and generate.
• Automations — The control center for Agents, Workflows, and Schedules.
• PDF — View, annotate, and extract from PDFs — fully indexed and AI-readable.
• Transcripts — Audio and video transcription with speaker detection — searchable, AI-readable, link-ready.
• Senses & Connections — How the world gets in — integrations, the browser extension, the desktop watcher, and direct ingestion.
• Desktop & Computer Use — What the River Desktop App unlocks — native files, screen access, and AI that operates your machine.
• Integrations — How River connects to the rest of your stack — 100+ services, two patterns.
• Gmail — Connect Gmail for full-inbox sync, AI triage, and one-click composition.
• Google Calendar — Sync your calendar as entities the AI can reason over and act on.
• Google Drive — Browse Drive, ingest files as entities, and reason over the contents with AI.
• Slack — Search Slack, post from River, and receive notifications in your channels.
• MCP Servers — Connect any Model Context Protocol-compatible tool server to River.
• Browser Extension — Clip any web page, selection, or screenshot from anywhere into River.
• Orgs & Members — How organizations, dataspaces, and member access fit together.
• Roles & Permissions — How access works at the Org, Dataspace, Space, and entity level.
• Sharing — Share individual entities, Groups, or whole Spaces — internally or with guests.
• Multiplayer & Presence — Real-time co-editing, cursor presence, and CRDT-based sync that never conflicts.
• User Profile — Set your identity, preferences, and AI personalization.
• Custom Views — Ask the AI for a dashboard, a tracker, or any new view of your data — and have it built on the spot.
• Custom Apps — Build full applications inside River — your own entity types, UI, data, and AI.
• Space Templates — Pre-configured Spaces for common workflows — one click to spin up a working environment.
• Keyboard Shortcuts — Move through River with your hands on the keyboard.
• How Privacy Works — What stays on your machine, what flows to River's cloud, and how you control both.
• Self-Hosted River — Run the full River stack on your own infrastructure — no cloud dependency.
• Teams Overview — How team Dataspaces, shared agents, and collaborative workflows work in practice.
• Admin Dashboard — Usage metrics, member management, and org-level controls.
• Billing & Usage — Plans, seats, AI usage budgets, and invoice management.

Notes#

• This documentation set is intentionally concise in the first iteration.
• Additional pages can be added without changing the route architecture.