← iLiveMyLifeFor developers · SDK · CLI · MCP

Your graph — from the command line,
and from your AI.

One open package gives you a TypeScript SDK, the ilml CLI, and an MCP server — so you can script your graph, or let Claude, Cursor and Windsurf work inside it directly.

npm: @ilivemylife/graph-sdk →Plugin: ilml-plugin-linkedin →

First · Install

One package — CLI, SDK and MCP.

Node 18+. One global install gives you the ilml command and the SDK.

install & sign in

npm install -g @ilivemylife/graph-sdk
ilml login
ilml doctor   # verify everything works

In your terminal · CLI

Drive your graph with `ilml`.

The full command set — and every command speaks text or --json, reads from stdin or files, and pipes into shell scripts.

ilml — command reference

# Explore

$ ilml tree# your whole graph, as a tree

$ ilml items <node># a node and its children

$ ilml itemHistory <node># every change — who, what, when

$ ilml search <node> "text"# search a node’s chat

$ ilml messages <node># read a node’s chat

$ ilml itemUsers <node># who has access

$ ilml itemSettings <node># a node’s AI / notification settings

# Ask the AI

$ ilml ask <node> "question"# ask Lifebot, in the node’s context

$ ilml send <node> "message"# post a message (optionally trigger AI)

$ ilml editSettings <node># switch AI provider / smart model per node

# Create & reorganize

$ ilml addItem <parent> --title …# create a node

$ ilml editItem <node> --title/--desc/--tags# edit a node

$ ilml moveItem <node> <from> <to># move to another parent

$ ilml reorderChild <parent> <from> <to># reorder children

$ ilml setPosition <node> <parent> <n># move to a position

$ ilml archiveItem / unarchiveItem <node># archive / restore

$ ilml upload <node> ./file# attach a file

# Collaborate

$ ilml request-access <node># ask to enter a private node

# Plugins

$ ilml plugin install <name># add a plugin (e.g. linkedin)

$ ilml plugin list / update / remove# manage installed plugins

$ ilml <plugin> <command># run a plugin command

# Setup

$ ilml login [--local]# sign in — global or per-project

$ ilml doctor# verify your setup

$ ilml config set <key> <value># configure

$ ilml logout# sign out

Pro

One CLI, many accounts. ilml login signs you in globally — every folder. Run ilml login --local inside a project to use a different account just there (personal vs work, or a dedicated bot account for an automation). Resolution order: local config → .env token → global → shell variable.

text or JSON — composable in shell scripts

ilml tree --json | jq '.[].title'              # machine-readable → jq
ilml items <node> --json > backup.json          # snapshot your graph
cat notes.md | ilml editItem <node> --desc -    # pipe content straight in

In your AI · MCP

Plug your graph into your AI.

One command connects the MCP server to Claude Code (Cursor, Windsurf and Claude Desktop are the same idea).

Claude Code — available in every project

claude mcp add --scope user ilml -- npx -y @ilivemylife/graph-sdk

Then just ask, in plain language:

Read my latest notifications and summarize what needs my attention.
What changed in my “Projects” node this week — and who changed it?
Create a task “Call the bank” under My Life, due tomorrow.
Search my whole graph for everything about the landing redesign.

In your code · SDK

Or script it yourself.

Typed TypeScript SDK (ESM + CommonJS): read and write nodes, ask Lifebot, upload files, replay every change, subscribe to live updates.

Read your graph

const me = await graph.me()
const items = await graph.items(me.rootItemId)
console.log(items[0].title, '→', items.slice(1).map(i => i.title))

Create nodes

const project = await graph.addItem(me.rootItemId, { title: 'My Project' })
await graph.addItem(project.id, { title: 'First task' })

Ask Lifebot — AI that knows the node (needs the 'assist' tag)

const reply = await graph.askLifebot(project.id, 'What tasks do I have?')
console.log(reply.content)

Replayable change history — who, what, when

const history = await graph.itemHistory(project.id)
// every edit on the node: who made it, what changed, and when

Upload a document, search the chat

await graph.uploadFile(project.id, './spec.pdf')
const hits = await graph.searchMessages(project.id, 'deadline')

11 runnable examples + full API on npm →

Extend it · Plugins

Install a plugin — or build your own.

Plugins install into your ilml CLI as packages. The LinkedIn plugin is the reference: it keeps a local mirror of your LinkedIn data and runs AI-assisted workflows under your direction — and doubles as the template for authoring your own.

install one / build your own

ilml plugin install linkedin     # from npm:ilml-plugin-linkedin
ilml plugin list                 # what's installed
ilml linkedin <command>          # run a plugin command
# author one → see examples/plugin-author.mjs in the SDK

npm: ilml-plugin-linkedin →Plugin-authoring example on npm →

Build on your graph.

Your data, your code, your AI — all on one open graph.

Start your graph →

Your graph — from the command line,and from your AI.