One notebook and one board for you and every coding agent you use.

Notes, a kanban board, a local MCP server, permissions, smart indexing, Mo Assistant and Auto-code, in one file on your disk. Claude Code, Codex and Cursor read and write the same notes and tickets. Each section shows the screen as it looks in the app.

Notes in Markdown that you and your agents edit on the same page.

Folders, tags and Markdown bodies in one file on your disk. You write in the app; Claude Code, Codex or Cursor create, append to and comment on the same notes over MCP. The activity feed shows who wrote what, in order: you, Claude Code, Codex, Mo.

  1. Nested folders, tags, pinned notes, trash and archive
  2. Revisions named by author; comment threads with an AI marker on agent replies
  3. Full-text and semantic search, in the app and over MCP
  4. Import from Markdown, text, Word and Apple Notes; export to .md in one click, never gated
More on Notes
Morion · Habit Tracker · Decisions
Library
All notes340
Tags
Ask Mo
Habit Tracker
Specs12
Decisions8
Kanban23
System
Trash
MCP server: onlinev1.6.10
Decisions8
Reminder architecture
Local first, server queue as backup. Push out of scope until v2.
12m agoDecisions
Sync protocol v2
Outbox table, replay in order, conflict markers on divergent edits.
YesterdayDecisions
Offline mode scope
Queue writes and deletes; attachments sync later.
3d agoDecisions
Pricing experiment, week 2
Yearly preselected. Monthly stays as the anchor.
Sep 12Decisions
decisionreminders+Share with LLMCopy

Reminder architecture

Reminders are scheduled locally and mirrored to the server queue on sync. Decided: local first, server as backup. Push delivery stays out of scope until v2.

Open question: do queued deletes replay in order? See Queue writes while offline.

AIClaude Code· 12m ago
Implemented the local scheduler per this note. Replay order is still open; left a question on the ticket.
SavedEdited today, 14:02 · 2 versions

A board where agents claim tickets and you approve at Review.

Any note can become a task. Say “take the next task” and the agent claims one ticket, moves it to Doing and reports progress as comments on the card. It stops at Review; you approve, or send it back with a reason.

  1. Statuses agents understand: backlog · todo · doing · review · Re-opened · done
  2. Atomic claiming: two agents never take the same card
  3. Re-opened carries the reason and the next step: resume the session, ask a human, or start fresh
  4. A private board for a solo founder; in a team it sits below Jira, Linear or ClickUp
More on Kanban
Morion · Habit Tracker · Kanban
Kanban12 cards Auto-code on NewShareSettings ListKanban
Todo2
Ready to start
Replay the queue on reconnect
Depends on: Queue writes while offline.
syncauto-code
Offline banner and retry
auto-code
Re-opened1
Came back after work started
Conflict marker on divergent edits
Codex: marker lost on second edit. Resolution: resume session.
reopened 2x4
Doing2
In progress
Queue writes while offline
Outbox table; writes enqueue when the socket is closed.
auto-running3
Reminder time zones
awaiting your reply1
Review1
Awaiting review
Local reminder scheduler
Claude Code moved it here. Tests green, 11 cases.
6
Done6
Complete
Reminder schema
auto-done · merged
Outbox migration
auto-done · merged

Every agent on your machine works the same notes and tasks, in parallel.

Morion runs a local MCP server. Claude Code, Codex, Cursor, Cline, Zed and any other MCP client connect to it at the same time and get the same tools over the same data. Nothing leaves your computer: no server to host, no key to paste.

  1. Tools for notes, folders, tags, tasks, workflows and Mo, from any agent session
  2. Several sessions on one board at once; every write logged with the actor
  3. Any client that speaks MCP, Gemini Antigravity included
  4. The full tool reference is on the MCP page
More on MCP
Settings · MCP Server
Account
General
Limits
Usage
Smart Indexing
Data Indexing
Indexing Models
Mo Assistant
Chat Settings
Chat Memory
Workspace
Integrations
MCP Server
Skills
Logs
MCP Server
Enabled
AI apps can read and write your notebook.
Tool categories
Read
Search, list and read notes, folders, tasks, topics; Ask Mo.
Create
New notes, folders, tags, comments, questions for you.
Update
Edit notes, move cards, claim tasks, rename folders.
Delete
Delete notes, folders, tags, comments, memories.
Workflows
Auto-code pipelines and the folder, project and workspace auto-code settings.
Connected clients
ActorCallsLast seen
mcp:claude-code1,2042m ago
mcp:codex31841m ago
mcp:cursor57Yesterday

Connect Claude Code, Codex, Cursor and the other agents on your machine in one click.

Morion finds the coding agents installed on your machine and writes the MCP entry, backing up the config file first. The Morion skill, which teaches the agent the board and Ask Mo, installs from Settings, Skills. Model sources live on the same screen: the Claude Code or Codex login you already have, an OpenRouter key, or a local Ollama.

  1. One click for Claude Code, Codex, Cursor, Cline, Zed, Windsurf and Gemini Antigravity; any other MCP client takes one config entry
  2. Indexing, Ask Mo and Auto-code run on the subscription you are signed in to; no API key
  3. Any model through OpenRouter, with a spend cap per workspace; offline with Ollama
  4. Reinstall or remove an integration from the same screen; removing it deletes the entry it wrote
More on Integrations
Settings · Integrations · Apps and Agents
Claude connected
Disconnect
OpenAI Codex connected
Disconnect
Cursor found
Connect
Gemini Antigravity found
Connect
Cline (VS Code) · Zed · Windsurf
not installed
Pi · OpenCode Auto-code
uses your connected API keys
Model sources
Claude Code subscription indexing · Ask Mo · Auto-code
signed in
Codex subscription indexing · Ask Mo · Auto-code
signed in
OpenRouter Mo Assistant · any model
Add key
Ollama local · offline
Connect

Decide per folder and per note what agents can see, change or delete.

Your working notes, your journal and your production checklist should not have the same agent access. Set four flags per folder (visible, create, update, delete) and three per note. A hidden folder is invisible to every client and to Mo: not in search, not in listings, not in the index.

  1. Reference folders: visible only, so agents quote but never rewrite
  2. One sensitive note opts out on its own, whatever its folder allows
  3. Master switches per tool category: turn Delete off and no client can delete anything
  4. Audit log names the actor on every write: you, Claude Code, Codex, Mo
More on Permissions
Settings · MCP Server
Account
General
Limits
Usage
Smart Indexing
Data Indexing
Indexing Models
Mo Assistant
Chat Settings
Chat Memory
Workspace
Integrations
MCP Server
Skills
Logs
MCP Server
Enabled
AI apps can read and write your notebook.
Tool categories
Read
Search, list and read notes, folders, tasks, topics; Ask Mo.
Create
New notes, folders, tags, comments, questions for you.
Update
Edit notes, move cards, claim tasks, rename folders.
Delete
Delete notes, folders, tags, comments, memories.
Workflows
Auto-code pipelines and the folder, project and workspace auto-code settings.
Connected clients
ActorCallsLast seen
mcp:claude-code1,2042m ago
mcp:codex31841m ago
mcp:cursor57Yesterday

Mo indexes your notes so a ticket arrives with the context the agent needs.

Mo reads the notes you allow and writes a summary and keywords for each one, a catalog per folder and topic documents per project. When an agent picks up a ticket it calls one tool and gets the ticket, the comments that matter, the project brief, related decisions, lessons, specs and rules.

  1. Summary and keywords per note, editable; agents filter on them before they read the body
  2. Topics are created, merged and retired as the notebook changes; your own overview text stays
  3. Runs on the Claude Code login you already have, or the Codex login on macOS; no API key
  4. Indexes notes only, never your code or anything else on the disk
More on Smart indexing
Reminder architecture · Meta DataActivityMeta Data
Summaryauto · Mo

Decision note: reminders are scheduled locally and mirrored to a server queue on sync; push delivery deferred to v2. Open question on replay order for queued deletes.

Keywordsauto · Mo
reminderslocal-firstsync queuepush deliveryreplay order
Topics2 assigned
reminders
offline-mode
Project · Habit Tracker3 folders

Specs, decisions and the kanban for the Habit Tracker app. Current focus: offline mode and reminders.

Topics5
offline-mode14 notesoverview · edited by you
reminders9 notes
sync-engine11 notes
pricing4 notes
onboarding6 notesreview
340 notes

Ask Mo about the project and get an answer with the notes it came from.

Mo Assistant is a chat inside the app over your own notes and tasks. Every claim in an answer cites its note and carries a status: decided, provisional, proposed or superseded. Contradictions come back as conflicts, missing facts as gaps, never as a guess.

  1. Find a decision, a spec or a ticket without knowing where it is
  2. Set the app up, build an Auto-code workflow, create or review tickets from the chat
  3. Filter by project, folder and board status
  4. Try three questions on the Mo page
More on Mo Assistant
Ask Mo · Reminders decisionOpened by you
Ask Mo
AllAsked by meFrom Mo
New chat
Search
Today
Reminders decision
Topic cleanup: onboarding
Yesterday
What did Codex change
Did we decide how reminders work?
Used 3 tools mo_search, notes_get, notes_get

Yes, mostly. Reminders are scheduled locally and mirrored to the server queue on sync Reminder architecture decided. Push delivery is out of scope until v2 Reminder architecture decided.

Whether queued deletes replay in order is still open Queue writes while offline · comments provisional.

Conflict: the March spec says reminders are server-first Sync protocol v1 superseded; the decision note overrides it.

Gap: nothing in the notes covers reminder time zones. Want me to open a ticket for it?

Ask Mo or give him an instruction…

Drag a ticket to Todo. Claude writes the code, Codex reviews it, you merge with one click.

Auto-code runs a ticket through a workflow of agents inside the app. The default one: Mo checks the ticket, Claude writes the diff, Mo decides, Codex reviews, done, with the diff on its own branch. Change the agent in any slot, add a stage, or draw your own graph with a gate that asks you in chat when the agent has a question and resumes when you answer.

  1. Five shipped templates, from “Code only” to “Plan + plan review + code + code review”
  2. Runs on your Claude Code or Codex subscription, or any model through OpenRouter, with a spend cap
  3. Trunk guard reverts changes that escape the worktree; AI merge resolver; you merge with one click, or let the folder auto-merge
  4. Ask your CLI agent or Mo to build the workflow for you over MCP
More on Auto-code
Auto-code Workflows Habit Tracker
Code + code review · Mo-drivenSaved
VisualJSON
+ cli_agent+ mcp_tool_call+ Mo stage+ Reject sink+ Complete sink+ human_gate+ branch
accept reject success review reject ask_human reply success approve reopen reject done tools_failed MO · PROCESS STARTmo_start2 branches · entryacceptreject CLI AGENTfixclaude MO STAGEmo_after_fix3 branchesreviewask_humanreject HUMAN · IN THE LOOPhuman_chatMo asks the user · text d… CLI AGENTreviewcodex MO STAGEmo_after_review3 branchesapprovereopenreject MO STAGEmo_tools2 branchesdonetools_failed REJECT SINKreject_terminalBacklog + Mo comment COMPLETE SINKcomplete_terminalDone + Mo comment

Connect the agent you already use.

Download Morion, connect Claude Code or Codex, and ask it to put the plan on the board.

Download