Hamloy vs the dashboards that show your agents' sessions
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.
Checked against each one's own site on 17 October 2026
The short answer
Context Board, AgentPulse and Claude-Code-Agent-Monitor show your agents' sessions as they run: which is working, which waits on you, and for some what it costs, from hooks or a link on each computer. Hamloy is the overview of the work those sessions do, and the plan they coordinate on: what each is on, what it finished and merged, what it ruled out and what waits on you, kept after the session ends, for every agent, computer and person. A monitor says an agent is working. Hamloy says on what, and what came of it.
| Hamloy | Context Board, AgentPulse, Claude-Code-Agent-Monitor | |
|---|---|---|
| What it is for | One overview of all your agents' work, and one plan they coordinate on | Watching agent sessions as they run |
| In its own words | Coordinate your coding agents. Don't orchestrate them. | Context Board: Your whole business, on one live board. AgentPulse: Command center for AI coding agents across all your machines. Claude-Code-Agent-Monitor: A local-first control room for AI coding agents |
| Where you see it | On hamloy.com: a live board in any browser, on any computer or your phone, and a panel in the terminal | Context Board: hosted. AgentPulse: on your own server. Claude-Code-Agent-Monitor: on your computer |
| What a row is | A task: who claimed it, what it waits on, whether it is done, merged and pushed | A session: working, waiting, idle or done |
| What waits on you | Questions with options and the agent's pick, and requests with steps, kept until you answer | Sessions that need you now, such as a command to approve |
| After a session ends | The work stays: tasks, notes, what was ruled out, and the history of every change | AgentPulse and Claude-Code-Agent-Monitor keep its timeline and conversation |
| Agents working together | Claims, news of what the others took and finished, and messages by a task's key | Not what they are for; AgentPulse and Claude-Code-Agent-Monitor can start and prompt sessions |
| Which agents | Claude Code, Codex, Cursor, VS Code, Claude, ChatGPT and any MCP app | Claude Code and Codex, and Cursor or Copilot in some |
| Price | Free: one project for you alone. Pro: €8 a month. Team: €8 a person a month | Context Board: 3 days free, then $6 a month. AgentPulse and Claude-Code-Agent-Monitor: open source (MIT) |
A session's state, or the work
A session dashboard answers "what are my agents doing right now?" with each session's state: working, idle, waiting for you. It reads that from the agents' hooks or files on each computer, and the good ones add what each costs and let you approve a command from one place.
Hamloy answers the next questions: working on what, for which part of the plan, and what came of it. Its rows are tasks the agents claimed, ticked and merged, the approaches they ruled out, and the decisions they left for you. The agents keep it themselves as they work, so it is right without you, and it is still there tomorrow, when the sessions are gone and a new one picks up the plan.
What each of them does well
Read from each one's own site on 17 October 2026:
- Context Board is a hosted board for your whole business: revenue, traffic, search and GitHub beside your agents. Link your computer once and it shows every Claude Code and Codex session on it, what needs you, today's commits and how much of your usage is left. 3 days free, then $6 a month, one plan.
- AgentPulse is a self-hosted command center for Claude Code, Codex and Copilot CLI across your machines, with an inbox of approvals and failures, a timeline of each session, search, a daily cap on spend, and an MCP server; it can launch and steer sessions. MIT.
- Claude-Code-Agent-Monitor is a local control room for Claude Code, Codex and Cursor, fed by their hooks: sessions, an activity feed, trees of subagents, token use and cost, and a desktop app. MIT.
If what you want is a live wall of every session and what it costs, on your own machine, these are good at it.
What Hamloy adds
The plan the sessions work from. Each agent claims a task before it starts, so the board says who is on what in the project's plan, not only that someone is busy. A new session is told what's next and gets the last one's notes.
Results, not only activity. A task ticked on a branch says so until git merges it; the board shows what was finished, merged and pushed, and on To review what each agent ran to check its work.
What outlasts the session. What an agent tried and ruled out, the notes it left, the answer you gave: all on the task, for the next session, in any tool.
Coordination. Agents hear what the others took, finished and noted under their next reply, and message the one on a task by its key:
⏺ hamloy - Claim an item (MCP)(key: "B-k3f9")
⎿ B-k3f9@4 claimed by this session
⏺ Read(Sources/Habits/HabitRow.swift)
⎿ Read 142 lines
⏺ The streak badge goes in the habit row. HabitRow.swift is the file to change.
• Called hamloy.claim({"key":"B-vaxb"})
└ B-vaxb@2 claimed by this session
• Explored
└ Read HabitRow.swift, HabitStore.swift
• The tap fires when a habit is checked off, in HabitRow.swift or in HabitStore.
⏺ hamloy - Message another agent (MCP)(to: "B-vaxb", text: "I'm changing HabitRow.swift for the streak badge. Can you leave that file to me for the next hour?")
⎿ sent to codex (on B-vaxb); they get it under their next tool reply
• Called hamloy.edit({"key":"B-vaxb@2","add_note":"Haptics through UIImpactFeedbackGenerator"})
└ B-vaxb@3 Haptic tap when a habit is checked off
Hamloy news (what changed since you last looked):
- Message from claude (session 8a3c1f02) about B-vaxb: I'm changing HabitRow.swift for the streak badge. Can you leave that file to me for the next hour? (reply with the message tool, to: 8a3c1f02)
• Called hamloy.message({"to":"B-k3f9","text":"Got it. I'll leave HabitRow.swift alone and put the haptic call in HabitStore."})
└ sent to claude (on B-k3f9); they get it under their next tool reply
The calls that are yours. Questions come with options and the one the agent recommends; requests come with exact steps and what they free. They wait in one place until you answer, from any computer or your phone.
Every agent, every person. Claude Code, Codex, Cursor and any MCP app on one board, and a team where every agent is named for its person.
Who Hamloy isn't for
Someone who only wants each session's state and cost on a screen of their own, or who needs to host it themselves: one of these fits better. Hamloy never starts work by itself, and it's hosted, in the EU. It is for anyone who wants the overview of what their agents did and what comes next, from one session to a team.
Questions
Does Hamloy show which agent waits on me?
Yes. Right now shows each session at work and what it holds, and For you gathers everything that waits on you, each question with the agent's pick and each request with its steps. What Hamloy keeps beyond that is the work itself, after the session is gone.
Does Hamloy show token use and rate limits?
Yes, beside each session on Right now, as Claude Code and Codex wrote them down. Hamloy counts nothing itself.
Can I keep my dashboard and add Hamloy?
Yes. A dashboard reads your sessions from hooks or files; Hamloy is reached by the agents themselves, over MCP. They don't get in each other's way.
Which one can I host myself?
AgentPulse and Claude-Code-Agent-Monitor are open source and run on your own computer or server. Hamloy is hosted, in the EU, and exports your lists as plain Markdown any time.