Local board · MCP sync · Mo work packets · Auto-code

An AI notebook
your agents can work from.

Morion is a local notebook and task tracker that speaks MCP. Send tickets to Claude Code, Codex, Cursor, or any agent; Mo packages the context around the work; Auto-code turns each ticket into a visible build, review, decision, and completion flow.

Local notes + kanban, free Two-way MCP sync with LLM agents Build · review · decide · complete
Morion
Launch tasks 11 cards
List Kanban
New
Note 3
Launch-week talking points
Competitor scan — April
Onboarding copy ideas
Backlog 2
Linux build CI matrix
Agent permission UI
Todo 3
Fix race in ingest worker
Retry logic for DMG download
Audit-log filter by agent
Doing 1
Kanban drag polish
claude-code
Review 1
Hybrid search rerank
cursor
Done 1
Sidebar groups refactor
1 agent working · audit log active
Updated just now
Works with Claude Desktop | Claude Code | Cursor | Cline | Zed | Windsurf | Codex CLI | Google Antigravity | any MCP client
The problem

Your agents need a place to work, not another prompt.

Modern coding work is already multi-agent: Claude Code, Codex, Cursor, maybe a cheap open model through OpenRouter. But the plan lives in chat, the tasks live somewhere else, and every agent starts from a thin ticket with no surrounding memory.

Tickets are too thin.

A card says "fix opening trainer hints." The useful context is somewhere else: related tickets, design notes, previous decisions, known risks.

Chats do not make a workflow.

One agent builds, another reviews, and the next step should be explicit. In chat, that turns into manual babysitting and copy-paste orchestration.

Memory is stuck inside vendors.

Claude, ChatGPT, Gemini, and local models all have different memory surfaces. Your project memory should be visible, editable, and on your disk.

What Morion gives you

Three layers. One local workspace.

Start with a useful local notebook and board. Add MCP so agents can read and write it. Add Mo and Auto-code when you want the board to become an agentic dev loop.

Layer 1 · Local workspace

A notebook and task board you actually use.

Notes, specs, comments, tasks, tags, folders, and six kanban statuses live in one local file. It is useful before any AI enters the room, which is why it works as the source of truth when agents do enter.

Layer 1 · Agent queue

A kanban your agents can claim from.

Drop work into Todo. Claude Code, Codex, Cursor, Cline, Zed, or Antigravity can claim a card atomically, update it through MCP, leave comments, and move it back to Review. Two agents never take the same job.

Layer 2 · MCP sync

Two-way sync with any LLM client.

Send a ticket to an agent in one click. Or finish a long chat and ask the agent to save the decision, create follow-up tasks, or move cards. Morion is not a read-only memory store; it is the shared workspace both sides can update.

Layer 2 · Local control

Your disk. Your keys. Your audit log.

No Morion cloud workspace, no telemetry, no per-request Morion tax. If you use a cloud LLM, you choose that provider. If you point Mo at Ollama, the loop can stay local. Every AI write is logged with the actor name.

Mo · work packets
Paid · BYO LLM key

Mo turns a ticket into a work packet.

When an agent picks up a card, Mo does not hand it a naked title. It packages the ticket, related cards, folder memory, decisions, open questions, risks, and recent activity. It is also the in-app assistant you can ask directly, and the decision node inside Auto-code workflows.

Meet Mo
Auto-code · closed beta
Closed beta · free open beta planned

Auto-code turns the board into a dev loop.

Compose a graph for each ticket: implementation, review, Mo decision, optional human gate, and completion. Use a fast model where speed matters, a stronger one where judgment matters, and keep the whole run tied to the same board.

See Auto-code
Day-to-day

Four stories that make it click.

This is the difference between "AI can see my notes" and "AI is working from the same operating system I use."

01 · Plan the project

A short chat becomes a real board.

Start with a messy idea: "ship a usage dashboard with billing alerts for the beta." Talk it through with Codex or Claude. Then ask it to create the MVP board in Morion. The result is not a doc you forget about — it is a queue agents can claim from.

For example
  • Create the folder, git repo, and GitHub repo; keep the project brief as a note next to the work.
  • Ask Codex to break the MVP into cards: data model, billing webhook, dashboard states, alert emails, smoke tests.
  • Every card is editable by you and claimable by agents. Planning does not die in chat.
codex · planning session
morion · cards created 40
Usage dashboard · MVP brief note
Usage metrics API todo
Billing alert emails todo
Create MVP tickets for #usage-dashboard
02 · Start the work

Give agents the whole work packet.

A bare ticket is rarely enough. Before an agent writes code, Mo gathers the surrounding context: the related tickets in the same group, the project brief, old decisions, open questions, risks, and recent activity. The agent starts with a focused packet, not your whole notebook.

For example
  • The "usage metrics API" ticket arrives with data-source notes, billing risks, and sibling UI cards.
  • A reviewer sees what the builder was trying to do, not just the diff.
  • Context is fresh because it comes from the board and notebook, not a stale mega-prompt.
mo · work packet
Ticket: connect usage metrics to the dashboard.
Include related cards, known risks, and the MVP brief.
packet assembled
Usage dashboard packet
Ticket + MVP brief + 4 sibling cards + billing risk notes + acceptance criteria...
risks billing
03 · Run the graph

Turn each ticket into a controlled graph.

Auto-code is the harness for the repetitive part of coding work. One stage writes the diff, another reviews it, Mo routes the outcome, and the card moves with a closing comment. Different model in every role, all on your keys.

For example
  • Use a fast, lower-cost model through OpenRouter for first-pass implementation.
  • Send the diff to Codex or Claude for a stricter review pass.
  • Let Mo decide whether to complete, reopen, reject, or ask you.
morion · workflow board
Todo 2
Usage metrics API
Billing alert copy
Doing 1
Dashboard loading states
fast model · building
Review 1
Webhook tests
reviewed
04 · Orchestrate batches

Let a supervisor manage the batch.

Auto-code runs a separate workflow for each ticket, so multiple cards can be in progress with different agents. A smart external supervisor can manage the batch: check what finished, resolve merge conflicts, promote the next safe set of cards, and help stuck agents through MCP.

For example
  • Every few minutes a supervisor agent checks the Morion board through MCP.
  • It sees which tickets are reviewed, which are stuck, and which backlog cards are unblocked.
  • It promotes the next safe batch instead of making you babysit the loop.
terminal · MCP supervisor batch
$ agent-loop
check Morion board every 4m
[00:04] 3 cards reviewed
[00:04] promote T18, T26
[00:08] open merge-conflict task
// per-ticket workflows stay in Morion
// batch decisions stay visible on the board
Pricing

Free for the board. $8/mo for Mo + Auto-code.

Free is the local notebook, kanban, and MCP sync your agents can already use. Paid adds Mo work packets, unlimited boards, granular permissions, and the Auto-code closed beta.

Free
$0

Full notebook, full MCP access, up to 2 kanban boards. The local workspace plus your external agents.

Mo + Auto-code
Paid
$8/ month
billed annually · or $16/mo monthly

Everything in Free + unlimited boards + per-folder & per-note MCP permissions + Mo work packets on your LLM key + Auto-code closed beta.

How it compares

Each tool covers a slice. Morion stacks them.

Obsidian is local markdown, but MCP and tasks are plugin-driven. Notion and Linear now have official hosted MCP, but they are cloud workspaces. Mem is AI memory, not an agent queue. LangGraph is the pure harness: powerful graphs, but you bring the app, storage, and board. Morion stacks the local workspace and the harness.

Morion
LangGraph Obsidian Notion Linear Mem
Local-first ~ self-host
Markdown-native notes
Kanban / task queue built in ~ plugin
Agent-claimable tasks (atomic) ~ custom ~ assign agents
Official MCP server ~ community plugin ✓ hosted ✓ hosted
Hybrid / semantic search built-in ~ plugin ~ AI search ~
Audit log of all AI writes ~ traces ~ Enterprise ~ Enterprise
Folder + per-note AI permissions Pro ~ page-level ~ team/app
Mo work packets + in-app assistant Pro Notion AI (cloud) Linear Agent Mem chat (cloud)
Agentic harness multi-model dev loop, graph/workflow runtime Pro ✓ framework ~ agents
Free for personal use ✓ OSS ~
No vendor lock-in ✓ OSS ~ ~ ~ export
✓ yes  ·  ~ partial / hosted / plugin / custom  ·  ✗ no
Morion

The only local workspace that combines a daily-use notebook, an agent-claimable task queue, and first-class MCP access. Every agent action is logged with the agent's name — you always know who did what.

The local-first foundation

Six reasons your data belongs on your disk.

Local-first is what makes the rest of Morion honest. The notebook, the kanban, MCP, even Mo — all of it gets stronger when there's no cloud workspace holding your data hostage.

Private by default
Your data, your disk.

Client NDAs, source code, unpublished specs, your journal — nothing is uploaded. Ever. 73% of enterprise AI-tool deployments fail security review; there's nothing to fail here.

Instant agent calls
No network round-trip.

Cloud MCP servers add 300ms+ per call. Morion runs in-process — tool calls complete under 100ms. When an agent makes 20 calls, the difference is "instant" vs "why is this so slow."

Offline when you need it
Plane. Train. Airgap.

Pair Morion with a local LLM (Ollama, llama.cpp) and the entire loop — notes, tasks, agent — runs without an internet connection. No "please reconnect" while you're thinking.

Zero per-request fees
Agents can hammer it.

Morion never charges per search, per task, per call. Your agent can make 1,000 tool calls overnight — the month-end bill stays the same. Only LLM API costs scale with usage.

The layer below the team
Private iterations, nothing leaked upstream.

Shared JIRA and AGENTS.md weren't built to hold your half-baked plans, personal scratchpads, or failed attempts. Morion sits one level below the team layer — yours, private.

Built to outlive us
Plain files. Outlive any vendor.

Open formats with decades of stability ahead of them. If Morion disappears tomorrow, your data is still readable in 40 years. Markdown export whenever you want. Try any of that with Notion.

Read the full case for Morion All six reasons in depth — local foundation, agent queue, MCP, Mo, economics, no lock-in.
Get started

Four steps. No account. No cloud.

Install, capture some notes or queue some tasks, connect your AI, and let your agents get to work — all on your disk.

01
Install Morion

Download the macOS app. Open it. No sign-up.

02
Write notes or queue tasks

Jot things you want to remember. Flip a folder to kanban and drop tasks your agents can pick up.

03
Connect your AI

One click per client — Claude Desktop, Cursor, Cline, Zed, Claude Code, Codex, Antigravity.

04
Ask or delegate

Ask Claude a question and it pulls context. Or say "take the next task" — it claims one, ships it, moves it to Review.

Download Morion
Free tier · $0 · Apple Silicon · Windows & Linux live
Then connect your AI

One click per client. No JSON to write.

Morion detects installed AI clients and wires itself into their MCP config. You click Connect, the client sees Morion next time it starts.

Connect an LLM client
Click Connect to wire Morion into your client's MCP config. Existing entries are preserved.
Claude Desktop
Cursor Connected
Claude Code Connected
Cline (VS Code)
Google Antigravity Connected
Zed
Windsurf
Codex CLI Connected
For unsupported clients, paste a snippet manually. Any MCP-compatible client works.

Or skip the AI entirely — Morion is a perfectly good notebook on its own.