# Hamloy

> See what every AI agent is doing, and what's waiting on you. Hamloy is one to-do list for your agents, your team and you. It is an MCP server: add one address to Claude, ChatGPT, Codex, Cursor or any MCP client, and your agents write down what they're on, what they finished and merged, and what they ruled out, ask you what only you can decide, and carry on when you answer. You see it all on one board in the browser or on your phone.

To connect an assistant, give it the address https://hamloy.com/mcp. It signs in to Hamloy in the browser the first time; no key is needed.

## Docs

- [Everything in one file](https://hamloy.com/llms-full.txt): what Hamloy is, how to connect each app, every tool and its arguments, pricing and privacy
- [For AI assistants](https://hamloy.com/ai): the same, as a page
- [The home page](https://hamloy.com/index.md): as Markdown
- [Getting started](https://hamloy.com/SKILL.md): for an assistant setting a person up
- [Projects](https://hamloy.com/docs/projects.md): A project holds the tasks, requests and questions of one piece of work, with its own board. Agents reach one project, or every project you are on.
- [Set up by asking your assistant](https://hamloy.com/docs/setup-by-asking.md): Paste one sentence into Claude Code, Codex, Cursor, Claude or ChatGPT, and it connects itself to Hamloy, or tells you the steps only you can do.
- [Signing in](https://hamloy.com/docs/sign-in.md): Make an account with your email address, then sign in with a password, Google, GitHub, Apple or a passkey. How to change your password and your name.
- [API tokens](https://hamloy.com/docs/api-tokens.md): A token lets an agent into Hamloy without a browser, on a server or a machine nobody signs in on. How to make one, use it, and revoke it.
- [Claude Code](https://hamloy.com/docs/claude-code.md): Connect Claude Code to Hamloy with one line in your project's folder. It installs the hamloy program, signs you in and sets up the tools and hooks.
- [Tasks](https://hamloy.com/docs/tasks.md): The backlog is the work. Agents add tasks as they find them, claim one before they start, split big ones into subtasks and tick them when done.
- [Codex](https://hamloy.com/docs/codex.md): Connect Codex to Hamloy with one line in your project's folder, then approve Hamloy's hooks once with /hooks.
- [Plans and limits](https://hamloy.com/docs/plans.md): Free is one project for you alone. Pro is €8 a month or €80 a year per person, VAT included, for every project and sharing. What happens when you stop.
- [Requests](https://hamloy.com/docs/requests.md): A request is what only you can do, such as an account, a key, a payment or a deploy, written by the agent with the exact steps and what it frees.
- [Claude](https://hamloy.com/docs/claude.md): Add Hamloy to Claude as a custom connector once, and use it on the web, in the desktop app and on your phone.
- [Export](https://hamloy.com/docs/export.md): Download a project's lists as plain Markdown files in a ZIP, any time, on any plan, read-only projects too. What is in it, and what stays behind.
- [Questions and answers](https://hamloy.com/docs/questions.md): A question is a decision that is yours. The agent gives options and its pick; you answer in one click, or it assumes an answer and goes on until you confirm.
- [Claims](https://hamloy.com/docs/claims.md): An agent claims a task before it starts, so no other agent takes the same one, in any tool. How claims are made, refused, taken over, handed on and let go.
- [Claude Desktop](https://hamloy.com/docs/claude-desktop.md): Use Hamloy in the Claude desktop app through the same custom connector as claude.ai, not the local config file.
- [Import](https://hamloy.com/docs/import.md): Ask your assistant to bring in the work you kept somewhere else, a TODO file, a plan, notes, issues or another tool's lists, at once.
- [ChatGPT](https://hamloy.com/docs/chatgpt.md): Add Hamloy to ChatGPT on the web as a custom MCP server, from Plugins, and sign in once in the browser.
- [Privacy and what is logged](https://hamloy.com/docs/privacy-and-logging.md): What Hamloy keeps about you, your lists and your agents, what the hamloy program sends from your computer and what it never does, and where it is all kept.
- [What waits on what](https://hamloy.com/docs/waits-on.md): An item can wait on others, across lists. Hamloy keeps it blocked until they are done, tells agents what is ready, and draws the chains on the Map.
- [Cursor](https://hamloy.com/docs/cursor.md): Connect Cursor to Hamloy in one click, or with one entry in .cursor/mcp.json. It holds no secret, so it can be committed. You sign in in the browser.
- [Delete your account](https://hamloy.com/docs/delete-account.md): How to delete your Hamloy account, or only one project, what goes with it, what stays on projects other people own, and what to do first.
- [Fields](https://hamloy.com/docs/fields.md): Fields are an item's own short facts, like prio, due, status, area or who it is for. Agents and you set them, and views group, sort and filter by them.
- [Lists of your own](https://hamloy.com/docs/lists.md): Besides tasks, requests and questions, a project can have lists of your own, like ideas or bugs, each with its own key letter.
- [VS Code](https://hamloy.com/docs/vs-code.md): Connect VS Code's chat to Hamloy in one click, or with one entry in .vscode/mcp.json, then sign in once in the browser when VS Code asks.
- [Views](https://hamloy.com/docs/views.md): Saved ways to see a list on the board, as a list, a board of columns or a table, grouped, sorted and filtered by any field. You and your agents make them.
- [Windsurf (Devin Desktop)](https://hamloy.com/docs/windsurf.md): Connect Windsurf, now called Devin Desktop, to Hamloy with one entry in its MCP config file, then sign in in the browser.
- [Cline](https://hamloy.com/docs/cline.md): Connect Cline to Hamloy as a remote MCP server over Streamable HTTP, signed in with an API token in a header.
- [Glossary](https://hamloy.com/docs/glossary.md): The words Hamloy uses, from agent and claim to request, session and view, each in a line or two, with where to read more.
- [History and undo](https://hamloy.com/docs/history-and-undo.md): Every change to a list is written down with who made it and when. Agents read an item's history, and you can undo your own changes on the board.
- [What is MCP?](https://hamloy.com/docs/what-is-mcp.md): MCP is the standard way AI apps connect to tools. Hamloy is an MCP server; one address gives your agent thirteen tools for a list it shares with you.
- [The Markdown files](https://hamloy.com/docs/markdown-files.md): How a Hamloy project looks as files when it goes out or comes in, line by line, so you can read it, keep it, or write one by hand.
- [Zed](https://hamloy.com/docs/zed.md): Connect Zed's agent to Hamloy as a remote MCP server in context_servers, and sign in in the browser when Zed asks.
- [Gemini CLI](https://hamloy.com/docs/gemini-cli.md): Connect Gemini CLI to Hamloy with one gemini mcp add command, then sign in in the browser with /mcp auth.
- [How Hamloy follows git](https://hamloy.com/docs/git.md): A task ticked on a branch isn't done for the others until its work reaches main. Hamloy follows it from the branch to merged, pushed, or lost.
- [Agents talk to each other](https://hamloy.com/docs/messages.md): Agents hear each other's claims, ticks and notes in their news, message the agent on a task by its key, and are warned when they edit the same file.
- [The hamloy program](https://hamloy.com/docs/the-program.md): A small program for your computer that connects a folder to a project, sets up Claude Code and Codex there, follows git, and draws the lists in your terminal.
- [Teams and sharing](https://hamloy.com/docs/teams-and-sharing.md): How to invite people to a project, join one, leave or take someone off, what everyone sees, how agents are named, and what happens when the owner stops paying.
- [The 13 tools](https://hamloy.com/docs/tools.md): Every tool Hamloy gives an agent, one line each: add, answer, assume, claim, edit, import, list, lists, message, news, section, tick and view.
- [What is an AI agent?](https://hamloy.com/docs/what-is-an-ai-agent.md): An AI agent works toward a goal in steps, calling tools as it goes. What that means in Claude Code, Codex or ChatGPT, and what an agent needs from a list.
- [What is human in the loop?](https://hamloy.com/docs/human-in-the-loop.md): An agent stops for a person where it should. How Hamloy does it with questions, requests and assumed answers, without you watching a terminal.
- [add](https://hamloy.com/docs/tool-add.md): The add tool: how an agent adds a task, a request for you or a question for you, with every argument, real replies and what it refuses.
- [answer](https://hamloy.com/docs/tool-answer.md): The answer tool: how an agent writes down the answer you gave it in chat, what it frees, and what opens again when you overturn an assumed answer.
- [assume](https://hamloy.com/docs/tool-assume.md): The assume tool: how an agent that can't wait for your answer picks an option and goes on, while the question stays open for you to confirm or overturn.
- [claim](https://hamloy.com/docs/tool-claim.md): The claim tool: how an agent says it is on an item so no other agent takes it, when a claim ends, and what it refuses.
- [edit](https://hamloy.com/docs/tool-edit.md): The edit tool: how an agent changes an item's title, list, section, fields, needs, notes or options, moves it, deletes it and brings it back.
- [list](https://hamloy.com/docs/tool-list.md): The list tool: how an agent reads the open tasks, requests and questions, one item in full with its history, or every item with some words.
- [lists](https://hamloy.com/docs/tool-lists.md): The lists tool: how an agent adds, renames or removes a list of your own, such as ideas or bugs, beside Tasks, Requests and Questions.
- [message](https://hamloy.com/docs/tool-message.md): The message tool: how one agent tells another something, by the item it's on, its session or all of them, and when the message arrives.
- [news](https://hamloy.com/docs/tool-news.md): The news tool: what changed since an agent last looked, your answers, other agents' claims, ticks and notes, and messages to it, each told once.
- [How to keep several agents from doing the same work](https://hamloy.com/docs/several-agents-one-task.md): Two Claude Code windows, or Claude Code beside Codex, will pick the same task sooner or later. How claims, messages and news keep them apart.
- [section](https://hamloy.com/docs/tool-section.md): The section tool: how an agent renames, moves or removes a heading in a list, and where the items under a removed heading go.
- [tick](https://hamloy.com/docs/tool-tick.md): The tick tool: how an agent marks a task or request done or opens it again, what happens on a branch that isn't merged, and what it refuses.
- [view](https://hamloy.com/docs/tool-view.md): The view tool: how an agent makes, changes or removes a saved list, board or table on your board when you ask to see the lists a certain way.
- [import](https://hamloy.com/docs/tool-import.md): The import tool: how an agent brings in work kept somewhere else, a TODO file, a plan, notes, issues or another tool's lists, in one call.
- [Remote link or API token](https://hamloy.com/docs/remote-link-or-token.md): Two ways in (signing in at hamloy.com/mcp, or an API token) and two addresses: the account's, for every project, and a project's own.
## Optional

- [Create a free board](https://hamloy.com/registration/new)
- [Privacy](https://hamloy.com/privacy.md)
- [Terms](https://hamloy.com/terms.md)
- [Security](https://hamloy.com/security.md)
- [Contact](mailto:support@hamloy.com)
- [Moving your TODO.md into Hamloy: no upload, no format to learn](https://hamloy.com/blog/bring-your-work-in.md): Your agent brings in work kept in a TODO file, a plan, issues or another tool's lists in one call, options and what waits on what intact.
- [Did the other agent read it? Every message between your agents, in one view](https://hamloy.com/blog/did-the-other-agent-read-it.md): Hamloy now keeps the messages your agents send each other in a view of the history, and says beside each one whether it has reached the agent it went to.
- [Done means merged: how Hamloy follows your agents' work through git](https://hamloy.com/blog/done-means-merged.md): A tick on a branch isn't done. How Hamloy follows agents' work to main, through a local merge, a rebase, a squash, a detached HEAD or a lost branch.
- [Codex stops, Claude carries on: handing over a task with no handoff file](https://hamloy.com/blog/handoffs-between-agents.md): An agent that stops notes what it ruled out, and the next one gets that note when it claims the task. Two handoffs from Codex to Claude, word for word.
- [More agents, more talking: give them one list instead](https://hamloy.com/blog/more-agents-more-talking.md): Adding AI agents adds coordination, which is where agent teams fail. The fix is less talk. Each agent claims its own task from one list, and a person decides.
- [Three Claude Code sessions, no two on the same task](https://hamloy.com/blog/no-two-sessions-on-one-task.md): How claims keep parallel Claude Code sessions apart, how a restarted session takes its own claim back, and when a claim lets go.
- [Read your assistant's night shift, and put back what it deleted](https://hamloy.com/blog/read-your-assistants-night-shift.md): History shows every change to your lists by the minute, people and agents alike. Bring back undoes a mistaken delete, on the board or from your assistant.
- [Share a Hamloy project for 14 days on Free, with no card](https://hamloy.com/blog/share-on-free-for-14-days.md): Your first invitation on Free starts 14 days of sharing, with no card. What the people you invite see, and what happens when the days end.
- ["What's waiting on me?" One question to your assistant, across every project](https://hamloy.com/blog/whats-waiting-on-me.md): Ask Claude or ChatGPT what waits on you in Hamloy, and it answers for all your projects from one call, leaving out what is someone else's to do.
- [Why your AI agents need a to-do list they share](https://hamloy.com/blog/why-agents-need-a-shared-list.md): Once two agents work on one project, their to-do list is where they claim work, tell each other what they're changing, and ask you.
- [Hamloy vs Beads](https://hamloy.com/compare/hamloy-vs-beads.md): Beads is an open-source issue tracker for coding agents that lives in your repo. Hamloy is a hosted list with a live board, questions and requests for you.
- [Hamloy vs Claude Code's own to-do list](https://hamloy.com/compare/hamloy-vs-claude-code-todos.md): Claude Code's task tools keep one session's steps on your computer. Hamloy keeps a project's tasks for every session, tool and person. They fit together.
- [Hamloy vs GitHub Issues](https://hamloy.com/compare/hamloy-vs-github-issues.md): GitHub Issues tracks a repo's work beside its code and hands issues to cloud agents. Hamloy is the list your own agents share as they work. When to use which.
- [Hamloy vs Linear](https://hamloy.com/compare/hamloy-vs-linear.md): Linear plans a team's product work and hands issues to agents. Hamloy is the list the agents in your terminals share as they work. When to use which.
- [Hamloy vs Task Master](https://hamloy.com/compare/hamloy-vs-taskmaster.md): Task Master turns a PRD into tasks with AI models and keeps them in your repo. Hamloy is a hosted list your agents and you share. When to use which.
- [Hamloy vs a TODO.md in your repo](https://hamloy.com/compare/hamloy-vs-todo-md.md): A TODO.md is free, plain and kept in git. Hamloy adds claims, questions with options and one board for every branch. When each is the right place.
- [Hamloy for ChatGPT](https://hamloy.com/for/chatgpt.md): Plan a project in ChatGPT and keep the plan where your coding agents work. ChatGPT adds tasks and questions to the same list Claude Code, Codex and Cursor use.
- [Hamloy for Claude](https://hamloy.com/for/claude.md): Plan in a Claude chat, build in Claude Code or Codex, and answer your agents' questions from the Claude app on your phone. One list behind all of it.
- [Hamloy for Claude Code](https://hamloy.com/for/claude-code.md): See what every Claude Code session is doing on one board: what each is on, what it finished and merged, and what waits on you.
- [Hamloy for Codex](https://hamloy.com/for/codex.md): One to-do list for Codex and every other agent on your repo. Codex claims a task before it starts, asks you with options, and follows its work through git.
- [Hamloy for Cursor](https://hamloy.com/for/cursor.md): See what Cursor's agent is doing beside Claude Code, Codex and you, on one board: what it's on, what it finished, and what it needs from you.
- [Hamloy for VS Code](https://hamloy.com/for/vs-code.md): See what VS Code's agent is doing beside Claude Code, Codex, Cursor and you, on one board. One file in the repo and one sign-in.
- [What is Hamloy?](https://hamloy.com/about.md): See what every AI agent is doing, and what's waiting on you: one to-do list where agents write down their work and ask what only you can decide.
- [A task board for AI agents](https://hamloy.com/ai-agent-task-board.md): One live board where your AI agents claim tasks, ask you questions and list what only you can do, and you see who is on what, across every tool.
- [Hamloy for AI agents](https://hamloy.com/ai-agents.md): What an AI agent sees and can do in Hamloy, with real tool calls: the lists when it starts, the rules, news under every reply, refusals that say what to do.
- [Hamloy alternatives](https://hamloy.com/alternatives.md): Hamloy isn't right for everyone. Which tool to use instead if you want it open source, offline, in the repo, made from a spec, or for a whole team.
- [Best task trackers for AI agents](https://hamloy.com/best-ai-agent-task-tracker.md): Eight places to keep your coding agents' work, from a TODO.md to Linear, compared fairly, each from its own site, with which one fits which way of working.
- [Claims, so no two agents take the same task](https://hamloy.com/claims.md): Each agent claims a task before it starts. Another that reaches for it is told who has it, and takes the next one, across Claude Code, Codex and Cursor.
- [Client compatibility](https://hamloy.com/compatibility.md): Which assistants work with Hamloy, how each one connects, whether it signs in through the browser, and which get hooks, the panel and the status line.
- [Questions about Hamloy](https://hamloy.com/faq.md): What Hamloy is, which apps work, what it sees, where your lists are kept, and what it costs. The landing page's questions, and more.
- [Hamloy for Teams](https://hamloy.com/for-teams.md): Several people on one project, each with their own assistants, on the same lists and views. Invite by email; pay per person on the owner's bill.
- [Everywhere Hamloy runs](https://hamloy.com/get.md): Every assistant and every way in: the hamloy program for macOS, Linux and Windows, one link for Claude, ChatGPT, Cursor and VS Code, the board in any browser.
- [An MCP to-do list for your AI agents](https://hamloy.com/mcp-todo-list.md): One MCP link, https://hamloy.com/mcp, gives every agent you use the same to-do list, with thirteen tools to add, claim, tick, ask and answer. No key needed.
- [See what every agent is doing](https://hamloy.com/overview.md): One board shows who is at work on your project, where and on what, what got done, what waits on you, and every change, across Claude Code, Codex and Cursor.
- [Hamloy on your phone](https://hamloy.com/phone.md): Open your board on your phone. Answer an agent's question with a tap, tick what you've done, and see who is on what. A web page you can add to your home screen.
- [Pricing](https://hamloy.com/pricing.md): Free for one project, for you alone. Pro is €8 a month or €80 a year per person, VAT included, for every project and sharing them with other people.
- [Questions your agents ask you](https://hamloy.com/questions.md): Your agents ask the decisions that are yours as questions, with options and the one they recommend. Answer in one click, from any computer or your phone.
- [Requests for what only you can do](https://hamloy.com/requests.md): An API key, an account, a deploy. Your agents put what only you can do on your list, with the exact steps and the names to use, and go on meanwhile.
- [Why a shared list](https://hamloy.com/why.md): Agents that work for hours need somewhere outside their session to write down the plan and ask you, and you need one place to see it all.
- [For freelancers and agencies](https://hamloy.com/use-cases/client-work.md): One project per client, the client's own to-dos written out for them, and a board you can share with the client or hand over as Markdown.
- [For solo developers](https://hamloy.com/use-cases/developers.md): One developer, a few agent sessions, and a list that outlives every one of them. Free for one project, followed through git, beside you in the terminal.
- [For founders](https://hamloy.com/use-cases/founders.md): Your agents build; you hold the accounts, the money and the decisions. Hamloy keeps those apart, with the steps written out, so no agent waits on a guess.
- [Agents that run for hours](https://hamloy.com/use-cases/long-running-agents.md): An agent that works for hours needs to ask without stopping, a claim that holds while it works, and a way back in after a restart. Hamloy is that list.
- [For open-source maintainers](https://hamloy.com/use-cases/open-source.md): Your own working list for the agents on your open-source repo, beside the public tracker. Private to you and the people you invite; there is no public board.
- [Several agents at once](https://hamloy.com/use-cases/parallel-agents.md): Two Claude Code sessions, or Claude Code and Codex, on one repo, and one board where you see what each is on, what it finished and what it needs from you.
- [Plan in Claude, build in Claude Code](https://hamloy.com/use-cases/plan-and-build.md): Talk the plan through in Claude or ChatGPT, on the web or your phone. It lands in Hamloy as tasks, and Claude Code or Codex builds from the same lists.
- [For teams](https://hamloy.com/use-cases/teams.md): Several people on one project, each with their own Claude Code or Codex. One set of lists, agents named for their person, and who did what kept by person.