Hub Protocol is an open REST contract. Any AI service that implements it can connect to your pod.
Switch models without losing context. Run different models for different tasks. Self-host Llama on your own hardware and connect it to your Synap pod.
Your data doesn't move. The intelligence is pluggable.
Current AI tools have no memory of your work. Every conversation starts from zero.
Your Synap pod stores everything: notes, tasks, projects, people, articles, files — with relationships between all of them. The AI sees your full entity graph, not just a chat history.
Ask "what did I learn about distributed systems last month?" and get a real answer.
AI agents in Synap never modify your data directly. Every write operation creates a proposal — a structured diff with reasoning that explains what changes are suggested and why.
You see it. You approve or reject. Only then does anything change.
Full history, full audit trail, undo at any granularity. This is what "human in the loop" actually means.
Complex requests are decomposed by an orchestrator that dispatches to specialists: Chat, Research, Code, Writing, Knowledge Search, Action, View Builder.
Each agent has its own tool set and constraints. Research can traverse your entity graph. Code can execute in a sandbox. Writing can access your document history.
You always see what's happening and why.
