innernet docs
One memory for every AI tool. innernet.live holds it, netti — the agent — keeps it current, and every AI you connect reads and writes it live over MCP. No copy-paste between sessions, no re-explaining yourself to every new chat, and nothing to maintain by hand.
There are three ways in:
npx innernet— one command signs you in and wires every AI tool on your machine (Claude Code, Cursor, Codex, Windsurf, Gemini CLI, Claude Desktop, VS Code, Cline, Zed…). Run it inside a repo and that folder gets a memory of its own. Get started →- One URL — paste
https://innernet.live/api/mcpinto any MCP client and sign in in the browser. Connect an AI → - REST API + SDK — build apps and agents on the same memory: namespaced memories for your own users, branchable versioned context maps, ranked search. API guide →
the shape of it#
Each project is a Context Map: dimensions (markdown documents like vision or technical), nodes (structured entities — people, decisions, artifacts), and a commit log (append-only history of every change). Branches fork the whole map; merges bring direction back to trunk.
On top of the raw stores, each project carries a capture protocol — instructions telling the AI what to save and how, tuned to this project. A logistics project and a screenplay don't get the same advice.
A dimension describes the present. When something is superseded — an approach, a tool, a plan — netti replaces it in the body and records one dated line under a ## history heading at the end of that dimension. So a session reading your memory never sees two versions of the truth side by side, and "why did we change this?" still has an answer. The commit log holds the rest.