Skip to content

Coordinate your coding agents. Don't orchestrate them.

One overview of everything your agents do. One plan they coordinate on.

For Claude Code, Codex, Cursor and anything that speaks MCP, with one agent or ten.

Create a free board
One evening on Pebble. Claude Code and Codex work in their terminals while the board shows each one's steps as they come. Codex asks which sign-in Pebble should have at launch and goes ahead with its pick, its settings screen to open again if you choose the other, and you confirm the pick from the board or your phone. One press on Give to… starts Claude Code on your Mac for Sign-in screen, as telling it to in a terminal of your own does; it claims it, is told codex edits the same file and asks codex, who is woken to answer. The first claude opens its pull request and ticks its task, and you look over what it wrote beside what Hamloy saw run before Git merges it.
Show Hamloy in

Works with anything that speaks MCP

  • Claude
  • ChatGPT
  • Claude Code
  • Codex
  • Cursor
  • VS Code

The same board, from one session to a team.

Each step works on its own.

1. One session

Walk away. The board still knows what it did, and what it needs from you.

What finished, what waits on you, and who was at work.

The board's While you were away card, after 10 hours: a question and a request wait on you, an answer was picked for you so the work could go on, two finished tasks wait to be looked over, three more finished, two of them merged, and claude and codex were at work.

What only you can do comes first, with each item named.

Whether git has the work, not only whether it was ticked.

A pick an agent made for you, waiting for your OK.

2. Many sessions

Tomorrow's session starts where tonight's stopped.

A new session is told what's next, and gets the last one's notes.

A new Claude Code session, the next morning, is told that codex is on Sign-in screen and that the streak counter is next. It claims it and gets the last session's notes: a skipped day keeps the streak, and counting by calendar week was ruled out.

Who is on what, so this session leaves it to them.

What the last session found and ruled out, handed over with the claim.

The most important task that's ready and free.

3. Many agents

Add a second agent. Each sees what the other took, said and finished.

What each agent took, and what waits on it.

The Map: codex is on Sign-in screen, which frees Settings screen and App Store screenshots once it is merged, and claude is on the streak counter, which frees Share a streak as an image.

Each agent's claim, as the other sees it.

Starts once the work it waits on is merged.

What finishing this one frees.

4. Many people

Bring in your team. Every agent is named for its person.

Every agent named for its person, and what's yours kept for you.

Here now: Mira's claude on the streak counter, Sara's codex on Sign-in screen and Sara's claude on Settings screen. App Store screenshots, ready to start, is for you.

Every agent named for its person.

Meant for you, so every agent leaves it to you.

Sara's two agents, side by side with yours.

Done counts once it reaches main.

Ticked on a branch isn't done until git merges it.

A branch on the board: Count a skipped day as kept was ticked on streak-counter. It is done there, not merged into main yet, and waits to be looked over.

The branch the work was ticked on.

Done here, and not counted done until git merges it.

Your agents keep the plan. Nothing they change is lost.

Every change with a name on it, and a way back.

History, today: Sara's codex finished Settings screen; Mira's claude deleted Old onboarding copy, which can be brought back; you set the streak counter's priority to high, which you can undo; Sara's claude went ahead on a question; and Mira's claude merged the work of a task.

A deleted item, brought back in one click.

Who changed what, agents and people alike.

Your own change, undone.

Keep your terminals. Hamloy sits beside them.

Hamloy never starts work by itself. Your agents run where they run now: in your terminals, your editor, Claude or ChatGPT. They keep the plan themselves, so you never write a ticket.

Create a free board

The button copies this, for Claude Code or Codex to set it up for you: Read https://hamloy.com/SKILL.md and help me get started with Hamloy.

Hamloy in Claude Code's status line, under a test run: the task this session holds, B-6die Streak counter on the home screen, then 1 for you and 4 ready.

Pricing

For one person

You and your own agents.

Free

For one project of your own.

€0

Free for one project

 

Create a free board

No card.

  • One project, for you alone
  • Every feature and every app
  • Agents are free, as many as you run
  • Export any time

All your projects in one overview

Pro

For everything you work on.

€8/month

VAT included, billed monthly

or €80 a year, two months free

Get Pro

Cancel any time. Nothing is deleted.

  • Unlimited projects of your own
  • Every feature and every app
  • Agents are free, as many as you run
  • Export always works, even after you stop

For your team

Everyone, and everyone's agents.

Team

For people who share the work.

€8/person/month

VAT included, one bill for everyone

or €80 a person a year, two months free

Start a team

Free for its first 14 days. No card.

A team of 4 is €32 a month. Everyone's agents come free.

  • Unlimited projects, shared
  • Owner, admins and members
  • Two-factor sign-in for everyone
  • Every feature and every app

Hosted in the EU. We never train on your lists.

Questions

Is Hamloy an agent orchestrator?

No. It never starts work by itself. Your agents run where they run now, in your terminals, your editor, Claude or ChatGPT; Hamloy is the plan they share and the page where you see it. When you want to, you can hand a task to an agent at work from the board, write to it, or open a new Claude Code or Codex for a task on a computer that said yes.

Is it worth it with one agent?

Yes. The overview is for you, not for the agents: what your agent is on, what it finished and merged, what it ruled out and what waits on you, kept after the session ends. With one agent across many sessions, each new one starts where the last stopped, with its notes, in another window or on another computer. Several agents and a team use the same board.

Do I have to keep the lists up to date?

No, your agents do. They claim, note, ask and tick as they work. You can add and move things on the board whenever you like.

What is MCP?

The standard way AI apps connect to tools. Hamloy is an MCP server: your agent gets tools like add, claim and answer.

Which apps work?

Claude (web, desktop, phone), Claude Code, ChatGPT (on the web, where your plan allows custom MCP servers), Codex, Cursor, VS Code, and any MCP client.

Do you see my code?

No. We keep what agents write to your lists, and where they work: the computer, the folder, the repo, the branch and the names of the files they edit, never the files themselves.

Where are my lists kept?

In a database on servers in the EU. Export them any time: plain Markdown you can read, keep and move.

Can I bring in my TODO.md?

Yes. Ask your agent to bring it in: it reads TODO.md, a plan, notes or another tool's lists and brings them in at once. On an empty project it offers to by itself.

I have several projects. Can I see what waits on me in all of them?

Yes, with one question. Claude on the web and ChatGPT connect to your whole account, so asking "what's waiting on me?" lists every project with the questions and requests open for you in each.

I use worktrees and branches. Is that one project?

Yes. Every worktree and branch of a repo shares one board.

Who is Hamloy not for?

Someone who wants a tool to start and run agents in parallel for them: use one of those, and Hamloy beside it for the overview. Someone who wants a project tracker for work no agent touches. And anyone who needs to host it themselves: Hamloy is hosted in the EU, with export to plain Markdown any time.

What happens if I stop paying?

Nothing is deleted. On Pro, one project stays open, the one you choose; the others turn read-only, and you can still read, export and delete them. A team's projects turn read-only for everyone in it until its owner chooses a plan again.

Keep your agents. Give them one plan you can see.

Free for one project. No card.

Create a free board