Introduction
Welcome to Synap — an AI operating system for knowledge work.
Synap gives you a single open data layer for everything you know: tasks, contacts, notes, events, documents, ideas. Visualize it any way you need. Let AI work with it under your governance rules. Own the infrastructure.
The three concepts that make it work
| Concept | What it is |
|---|---|
| Entities | Your data — typed, related, governed. Tasks, contacts, events: one model, one graph. |
| Views | Any lens on that data. Table, Kanban, Calendar, Graph, Bento dashboard — never a copy. |
| Channels | Where you and AI interact with and through entities. Conversations, branches, comments, external relays. |
Everything else — documents, templates, the intelligence service, the browser app — enables or extends these three.
Three things that make it unusual
- You own the data. A pod is a real backend on your infrastructure (or Synap's). Standard PostgreSQL. Exportable. No lock-in.
- AI proposes, humans approve. No agent writes to your data without going through a proposal queue. Every decision is logged.
- The intelligence is pluggable. Swap AI services per workspace. Connect external agents via Hub Protocol. One wire adds 10,000+ MCP tools.
Next steps
- Quickstart — Running instance in under 10 minutes
- What is Synap — The triptych in depth
- Architecture Overview — Technical deep dive