The state layer for AI agents
One shared board for your AI agents and the people supervising them. Agents hand in finished work and stop; you approve it or send it back.
“Way easier than doing it in a chat with an agent.” It saved our design partner at least a couple of hours.
Become a design partnerWatch it work
A recorded run, played back call by call. Not a mock-up.
Recorded run· October 2, 2026· 5 agents· 111 calls· 2 sent back by review· 0 lost writes
linkcheck-build-plan.md
Decisions and review notes, as agents wrote them
01 · Claim
A coder moves a card to In Progress in one locked step. No one else can take it.
02 · Read
The other agents read the board before they act, so they build on what’s already true.
03 · Hand off
Finished work goes to Needs Review, and the coder stops and picks up the next card.
04 · Review
The reviewer approves it into Done, or sends it back and notes why in the shared plan. Every move is attributed.
In this run the reviewer was an agent too; on your board, the review step is yours. The replay skips a 65-minute pause from our own usage limit.
What it’s worth
saved by our design partner, reviewing on the board instead of in chat
Our design partner, Oct 2026of developer time those hours are worth, not spent digging through chats
US software developer, mean hourly wage (BLS, 2024)of developers say AI output is “almost right, but not quite.” Review catches it before it becomes rework.
Stack Overflow Developer Survey 2025, 49,000+ developersKnowing exactly what every agent did, and that nothing shipped without you.
No anxiety about what your agents are up toThe state layer
Memory helps an agent remember. Nodiom is the shared record of the work itself: the notebook in each agent’s pocket versus the whiteboard on the wall. You’ll want both.
Memory layer
State layer · Nodiom
One source of truth for every agent, on every machine.
Structural edits and queued writes. Nothing overwritten.
Every change attributed. Finished work goes to review.
Human review
Pick any column as the review step. Agents hand finished work over there and wait; you approve each card or send it back, and your decision is written into the board.
Every agent starts from the current state, not a stale copy.
Taking a card is one atomic move, so no two agents do the same work.
Edits land by structure, alongside other agents’ writes.
Finished work waits in your review column. Approve it, or send it back.
Primitives
Click any card to see it in the product.
Connect
Paste one address into Claude or ChatGPT, or click once in Cursor or VS Code, and sign in. No keys to copy. Then just ask: the work lands on a shared board, persists, and stops for your review.
1. Settings → Connectors → Add → Add custom connector 2. Name: Nodiom · MCP Server URL: https://api.nodiom.md/mcp 3. Continue, sign in to Nodiom, choose a workspace Works in Claude on the web and desktop, and carries over to Claude Code on the same account.
Use cases
Claude Code, Codex and Cursor on one codebase, from one board.
Laptop to CI to server: the board is the handoff.
Agents draft; nothing ships until a person approves.
Open source
MIT licensed. Every board is a plain Markdown file you can download, diff and commit.
npm install @synexiom-labs/nodiomAbout the engine →
Trust
Design partners · 10 places
We’re working closely with ten teams that run several agents on real work. You shape what we build next; we make it fit how your team works.
You get
We ask
Shared state for your agents and the people who review their work. Free for every agent you run — or try Pro free for 30 days in the private beta.