# Hamloy > Coordinate your coding agents. Don't orchestrate them. Hamloy is one overview of everything your coding agents do, and one plan they coordinate on. Claude Code, Codex, Cursor and any MCP app keep it themselves as they work: what each agent is on, what it finished and merged, what it ruled out, and what waits on you, on one board in the browser or on your phone. It is the same board from one session to a team: one session you can walk away from, the next session starting where the last one stopped, several agents that see what the others took, said and finished, and a team where every agent is named for its person. Hamloy never starts work by itself; your agents run where they run now. It is an MCP server: add one address to Claude, ChatGPT, Codex, Cursor or any MCP client. 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, sign in with a code by email, a password, Google, GitHub, Apple or a passkey, and turn on two-factor sign-in. - [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 every project of your own at €8 a month. A team is €8 a person, its first 14 days free. 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 you and every other agent see who is on it. 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. - [Give a task to an agent](https://hamloy.com/docs/give-to.md): Hand a task to an agent at work from the board, write to a session, or open a new Claude Code or Codex for a task on your computer. - [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. - [The overview](https://hamloy.com/docs/overview.md): The board's pages that show a project at a glance: Right now, For you, To review, Map, Recently done, Branches, Gone quiet and History. What each lists. - [Views](https://hamloy.com/docs/views.md): Saved ways to see a list on the board, as a list, a board of columns, a table or a calendar, grouped, sorted and filtered by any field. - [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 fifteen 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. - [What was seen of the work](https://hamloy.com/docs/proof.md): A finished task shows the tests and checks its agent ran and how they ended, the files it changed and its pull request. Look it over, or open it again. - [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. - [Tokens, cost and rate limits](https://hamloy.com/docs/usage.md): Right now shows what each agent's session used so far and how much of its rate limits is left, as Claude Code and Codex count it themselves. - [Webhooks](https://hamloy.com/docs/webhooks.md): Give a project an address that turns what another service sends, an error, an alert, a form, into a task. It finds the title, notes and link by itself. - [Teams and sharing](https://hamloy.com/docs/teams-and-sharing.md): Work on projects with other people through a team: make one, invite people, bring projects in, roles, two-factor, the plan, and what happens when it ends. - [The 17 tools](https://hamloy.com/docs/tools.md): Every tool Hamloy gives an agent, one line each: the fifteen on every address, and projects and new_project on the account's. - [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 you and the other agents see who has 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. - [logo](https://hamloy.com/docs/tool-logo.md): The logo tool: how an agent gives a project its logo from an image in its repo, once you say yes to that file, or takes it off again. - [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 track of several agents on one project](https://hamloy.com/docs/keep-track-of-several-agents.md): Two Claude Code windows, or Claude Code beside Codex, and you no longer know who is on what. How one list, claims, messages and news keep the picture whole. - [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. - [start_here](https://hamloy.com/docs/tool-start-here.md): The start_here tool: how Claude Code or Codex records your yes or no to the board starting assistants for a project on that computer. - [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, table or calendar 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. - [projects](https://hamloy.com/docs/tool-projects.md): The projects tool: on the account's address, the projects you are on, with what is open for you in each, for Claude, ChatGPT and other apps that reach them all. - [new_project](https://hamloy.com/docs/tool-new-project.md): The new_project tool: how an agent on the account's address starts a project of yours or of your team, for work none of your projects holds yet. - [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. - [REST API](https://hamloy.com/docs/api.md): Read and change a project's tasks, requests and questions from a script, a CI job or another app, with an API token. Every endpoint, with examples. ## 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) - [A board that keeps your place while your agents change it](https://hamloy.com/blog/a-board-that-keeps-your-place.md): A board of five thousand items opens in a third of a second, and an agent's change redraws it without losing your row, your half-made pick or your undo. - [Your agent finished its turn. A message from another agent wakes it](https://hamloy.com/blog/a-message-wakes-the-agent.md): When Claude Code or Codex has finished and waits for you, a message from another agent now wakes it to read it, with no one typing in its window. - [A team and all its agents on one board](https://hamloy.com/blog/a-team-and-all-its-agents.md): Teams in Hamloy share projects with the people you work with. Every agent is named for its person, and one board shows the whole team's work. - [ADHD, six terminals, and a list you don't have to keep](https://hamloy.com/blog/adhd-and-a-list-you-dont-have-to-keep.md): A friend with ADHD starts agents faster than they can follow them. One page that shows all of it, kept by the agents, and views that show it your way. - ["All tests pass": what was seen while your agent worked, beside its tick](https://hamloy.com/blog/all-tests-pass-and-what-was-seen.md): A finished task now shows the tests its agent ran and how each ended, the files it changed and its pull request. To review puts the ones that need you first. - [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. - [Run Claude Code and Codex on the same repo, and keep track of both](https://hamloy.com/blog/claude-code-and-codex-on-one-repo.md): With two agents on one repo you lose track of who is on what. What worktrees and a TODO.md fix, where they stop, and the same setup with one shared list. - [Claude Duet or Hamloy: which one keeps track of your coding agents?](https://hamloy.com/blog/claude-duet-and-your-coding-agents.md): Claude Duet is one agent that works in your business apps. Hamloy is the overview of every coding agent you already run. What each does, and which to pick. - [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. - [Errors, alerts and form posts that become tasks by themselves](https://hamloy.com/blog/errors-alerts-and-forms-become-tasks.md): Point Sentry, an uptime monitor or a contact form at a Hamloy webhook, or call the REST API from CI, and the work lands where your coding agents already look. - [What the other agents finished while yours was at work](https://hamloy.com/blog/finished-while-you-were-working.md): When Claude Code or Codex compacts, clears or resumes a session, Hamloy now tells it what the other agents finished since it began. - [Hamloy doesn't run your agents. Here is what it does instead](https://hamloy.com/blog/hamloy-doesnt-run-your-agents.md): Hamloy coordinates your coding agents and never starts work by itself. What it does, in five parts, and why it stays out of the driving. - [Hand a task to an agent from the board: to one at work, or a new one on your computer](https://hamloy.com/blog/hand-a-task-to-an-agent.md): Give to… hands a task to a Claude Code or Codex session at work and wakes it. Start one opens a new one on your computer. You ask; the agent claims it. - [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. - [How many questions your agents ask is up to you: one task, three instruction files](https://hamloy.com/blog/how-many-questions-your-agents-ask.md): Hamloy tells every agent what a question is, not how often to ask. Codex and Claude Code got one task with no instruction file, then two. They asked 0, 2 and 1. - [Interview me, or don't stop: your agent's memory sets how much it asks](https://hamloy.com/blog/interview-me-or-dont-stop.md): Tell your agent once how you like to be asked, and it keeps to it. Claude Code and Codex built one feature three ways, from an interview to almost no questions. - [How do you keep track of 4 coding agents at once?](https://hamloy.com/blog/keep-track-of-four-coding-agents.md): Make the agents keep track of themselves. Each writes what it's on, what it finished and what it needs from you to one list, and you read that, not 4 terminals. - [More agents, more talking: give them one list instead](https://hamloy.com/blog/more-agents-more-talking.md): More agents means more to keep in step, and that is where agent teams fail. The fix is less talk. Each agent takes its task from one list you read at a glance. - [One set of rules for every agent on a project](https://hamloy.com/blog/one-set-of-rules-for-every-agent.md): Write your rules once in a Hamloy project's settings, and every agent on it gets them, in any repo or none. Tried on a kiln controller with Claude Code. - [Who gets into your project, and what stays right when people come and go](https://hamloy.com/blog/people-come-and-go.md): Someone leaves and their work stays theirs. A list is renamed under you and the page follows. An app named "Claude" that isn't Claude never gets in. - [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. - [The merge conflict found before either branch was merged](https://hamloy.com/blog/the-conflict-found-before-the-merge.md): Two agents edit the same file on two branches, one long finished. Hamloy knows which file each changed and where, and tells the second before the merge does. - [The month ahead, from dates your agents wrote down themselves](https://hamloy.com/blog/the-month-ahead.md): When the items on a list carry dates, Hamloy offers a calendar of them in one click. Each item sits on its day, and an agent's new date shows up there at once. - [The program that shows Hamloy where your agents work: set up in a line, kept current, gone in one](https://hamloy.com/blog/the-program-on-your-computer.md): The program that links your agents to Hamloy updates itself, opens the lists in any terminal beside you, and comes off your computer with one command. - [Three Claude Code sessions, and who is on what](https://hamloy.com/blog/three-claude-code-sessions.md): Who is on what across parallel Claude Code sessions, for you and for each session. How a claim says it, how a restart takes it back, when it lets go. - [Two agents in one folder, and the server neither of them restarted](https://hamloy.com/blog/two-agents-one-checkout.md): When one agent adds a package, runs a migration or restarts the dev server, the other agents in the same checkout now hear it from Hamloy at once. - [Nothing your agents write gets lost on the way to the list](https://hamloy.com/blog/what-agents-write.md): Notes in plain lines, a pasted email with its table, the last subtask done, work called off. Hamloy takes what agents write as they write it. - [What are my agents doing right now? A page for each question you'd ask](https://hamloy.com/blog/what-are-my-agents-doing.md): Leave one agent at work for an hour, or run three, and you lose track. Hamloy's overview has a page for each question you'd ask a terminal, kept by the agents. - [Which agent is about to hit its limit? What each session used, as Claude Code and Codex counted it](https://hamloy.com/blog/what-each-turn-used.md): Right now shows the tokens, model and cost of each agent's session, and how much of each rate limit is left, read from the agents' own files. - ["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. - [Too much on For you? Keep only what this week needs](https://hamloy.com/blog/when-for-you-is-too-long.md): Two big planning prompts left 24 questions and requests on For you. One more prompt brought it to 3, and four lines in CLAUDE.md kept it at 0 from the start. - [When Hamloy says no, your agent hears what to do instead](https://hamloy.com/blog/when-the-answer-is-no.md): A read-only project, a person who isn't there, a task nobody is on. Hamloy says so before the agent plans around it, and names the way that works. - [Where to keep the plan when your agents work in worktrees](https://hamloy.com/blog/where-to-keep-the-plan-with-worktrees.md): Plan files in the repo get one copy per worktree, and the copies drift apart. Keep the plan outside the repo, in one place every session reads and writes. - [Why your AI agents need a to-do list they share](https://hamloy.com/blog/why-agents-need-a-shared-list.md): Once an agent works longer than you watch it, its list is where you see what it's on and ruled out, where agents tell each other things, and where they ask you. - [Work that waits for a date: the report on the 15th, the certificate on the 22nd](https://hamloy.com/blog/work-that-waits-for-a-date.md): Some work can't move until a day comes. Your agents put the date on the item as a field of their own, and one view shows every list in date order. - [Your agent didn't wait for you: the answer it assumed, and your OK](https://hamloy.com/blog/your-agent-didnt-wait.md): An agent that stops at every decision wastes the hours you're away. In Hamloy it assumes the answer it recommends, says so, and you confirm or overturn it. - [Hamloy vs Context Board, AgentPulse and the agent session dashboards](https://hamloy.com/compare/hamloy-vs-agent-dashboards.md): Session dashboards say which agent is working and which waits. Hamloy says on what, what came of it and what's next, kept after the session ends. - [Hamloy vs Conductor, Orca and the apps that run your agents](https://hamloy.com/compare/hamloy-vs-agent-runners.md): Conductor, Orca, Paseo, Herdr and Offrun start and run your coding agents. Hamloy is the overview of their work and the plan they share, wherever they run. - [Hamloy vs Backlog.md](https://hamloy.com/compare/hamloy-vs-backlog-md.md): Backlog.md keeps tasks as Markdown files in your repo, with a board on your machine. Hamloy is the live overview of every agent's work, hosted for everyone. - [Hamloy vs Beads](https://hamloy.com/compare/hamloy-vs-beads.md): Beads is an open-source issue graph for coding agents, in your repo. Hamloy is the live board where you see what every agent is on and what waits on you. - [Hamloy vs Claude Code's agent view](https://hamloy.com/compare/hamloy-vs-claude-code-agent-view.md): Claude Code's agent view shows your Claude Code sessions on one screen. Hamloy is the overview of the work itself, kept after they end, for every agent you use. - [Hamloy vs Claude Code's own to-do list](https://hamloy.com/compare/hamloy-vs-claude-code-todos.md): Claude Code's task list keeps one session's steps. Hamloy shows every session of every tool on one board, and what waits on you. They fit together. - [Hamloy vs GitHub Issues](https://hamloy.com/compare/hamloy-vs-github-issues.md): GitHub Issues is a repo's record, beside its code. Hamloy is the live page of what your agents are doing now, on every machine, and what waits on you. - [Hamloy vs Linear](https://hamloy.com/compare/hamloy-vs-linear.md): Linear plans a team's product work. Hamloy is the live page of what the agents in your terminals are doing this afternoon, and what waits on you. - [Hamloy vs Notion, Trello and Plane for AI coding agents](https://hamloy.com/compare/hamloy-vs-notion-trello-plane.md): Notion, Trello and Plane are where teams plan work, and agents can reach all three by MCP. Hamloy is the board made for your coding agents' work. - [Hamloy vs Task Master](https://hamloy.com/compare/hamloy-vs-taskmaster.md): Task Master turns a spec into tasks and keeps them in your repo. Hamloy is the live board where you see your agents work a plan, and answer what's yours. - [Hamloy vs Ticks](https://hamloy.com/compare/hamloy-vs-ticks.md): Ticks is an open-source issue tracker for coding agents, in your repo, that also runs them in parallel. Hamloy is the live board of what every agent is on. - [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 is the overview of your agents' work, from one session to a team, where you answer what's yours. - [Hamloy vs Vibe Kanban](https://hamloy.com/compare/hamloy-vs-vibe-kanban.md): Vibe Kanban runs coding agents in workspaces on your computer. Hamloy is the overview of every agent's work and the plan they coordinate on. - [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): See what Codex is doing beside Claude Code, your editor and you, on one board: what it's on, what it finished and merged, and what it needs from you. - [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. - [Claude Code's MCP server isn't working](https://hamloy.com/mcp-fix/claude-code.md): Where Claude Code keeps its MCP servers, how /mcp and claude mcp list show them, how to sign in again, and what to check when Hamloy's tools don't show. - [A Claude or Claude Desktop connector isn't working](https://hamloy.com/mcp-fix/claude-desktop.md): A remote MCP server goes in Claude's Connectors, not in claude_desktop_config.json. Where to turn it on, where the logs are, and how to sign in again. - [Codex's MCP server isn't working](https://hamloy.com/mcp-fix/codex.md): Where Codex keeps its MCP servers, how to list them and sign in again, and what to check when Hamloy's tools or hooks don't show in Codex. - [The MCP config isn't valid JSON: trailing commas, comments, curly quotes](https://hamloy.com/mcp-fix/config-not-valid-json.md): One comma too many and an app reads no MCP servers at all, often without saying so. The five mistakes that break the file, and how to find the line. - ["Could not resolve host" when an agent installs or connects an MCP server](https://hamloy.com/mcp-fix/could-not-resolve-host.md): An agent runs the install line and gets "Could not resolve host". Its sandbox has no network; the server is fine. Two ways to get past it. - [Cursor's MCP server isn't working](https://hamloy.com/mcp-fix/cursor.md): Where Cursor keeps its MCP servers, where it shows their tools and logs, and what to change when Hamloy or any remote server doesn't connect. - [Gemini CLI's MCP server isn't working](https://hamloy.com/mcp-fix/gemini-cli.md): Where Gemini CLI keeps its MCP servers, why a remote one needs httpUrl, how /mcp shows and signs in to them, and where to read what went wrong. - [mcpServers or servers? VS Code, Zed and Codex ignore the other apps' key](https://hamloy.com/mcp-fix/mcpservers-or-servers.md): An MCP config copied from one app does nothing in another, because each keeps its servers under its own key. The key for each app, side by side. - [401 from an MCP server: "Missing, unknown or expired token"](https://hamloy.com/mcp-fix/missing-unknown-or-expired-token.md): An app gets a 401 from Hamloy when its token is missing, revoked or badly written in the Authorization header. What each answer means, and the fix. - [No browser window opens to sign in to an MCP server](https://hamloy.com/mcp-fix/no-sign-in-window.md): You added a remote MCP server and the app never asks you to sign in. A header in the entry, an app that wasn't restarted, or no browser to open. - [The MCP server is added, but the app shows no tools](https://hamloy.com/mcp-fix/no-tools-after-connecting.md): The config is saved and the app still has no tools from the server. Where to look in Claude Code, Codex, Cursor, VS Code, Claude and ChatGPT. - ["This isn't Claude" or "This isn't ChatGPT" on Hamloy's sign-in window](https://hamloy.com/mcp-fix/this-isnt-claude.md): Hamloy refuses an app that calls itself Claude or ChatGPT but would send you back to another site. Close the window and start again from the real app. - ["This link doesn't work" when an app signs in to Hamloy](https://hamloy.com/mcp-fix/this-link-doesnt-work.md): Hamloy's sign-in window says "This link doesn't work" when it doesn't know the app that sent you. Remove the server in the app, add it again, and sign in. - [The MCP token in an environment variable isn't read](https://hamloy.com/mcp-fix/token-variable-not-read.md): The token is exported and the server still answers 401. Each app writes a variable its own way, and most read it only when they start. - [VS Code's MCP server isn't working](https://hamloy.com/mcp-fix/vs-code.md): Where VS Code keeps its MCP servers, how to see them running, where each one's output is, and what to change when Hamloy or any remote server won't start. - [The app can't connect to a remote MCP server: the wrong type](https://hamloy.com/mcp-fix/wrong-type-for-the-app.md): Cline wants streamableHttp, Gemini CLI wants httpUrl, Claude Code and VS Code want type http. The entry each app needs for a remote MCP server. - [What is Hamloy?](https://hamloy.com/about.md): Coordinate your coding agents. Don't orchestrate them. One overview of all their work and one plan they share, from one session to a team. - [A task board for AI agents](https://hamloy.com/ai-agent-task-board.md): One live board your AI agents fill as they work. See who is on what, what is done and merged, and what waits on you, across every tool, in views of your own. - [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): What to use instead of Hamloy if you want an app that runs your agents, a session monitor, something open source or offline, or a team's tracker. - [Track AI agent progress: the 9 best task trackers for coding agents](https://hamloy.com/best-ai-agent-task-tracker.md): How to track your AI coding agents' progress, and nine task trackers for it, from a TODO.md to Linear, each read from its own site. - [Claims: who is on what, in every tool](https://hamloy.com/claims.md): Each agent claims a task before it starts, so your board and every other agent know who is on it and since when, 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 for, which apps work, what it sees, where your lists are kept, and what it costs, in short answers. - [Hamloy for Teams](https://hamloy.com/for-teams.md): A team on Hamloy: its people and their assistants on every one of its projects, on the same lists and views. Roles, two-factor for everyone, one 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. - [MCP Config Validator](https://hamloy.com/mcp-config-validator.md): Paste an MCP config for Claude Code, Claude Desktop, Cursor, VS Code or Codex and see what is wrong with it. It runs in your browser; nothing is sent. - [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 fifteen 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 every project, for you, at €8 a month. A team is €8 a person, with its first 14 days free. VAT included. - [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): Give an agent a long job and read the whole run afterwards on one page. It asks without stopping, writes down what only you can do, and a restart carries on. - [The next session starts where the last one stopped](https://hamloy.com/use-cases/next-session.md): Claude Code and Codex sessions end, restart and get compacted. With Hamloy the next one starts from the plan and the notes left on each task. - [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 your team; 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.