Blog
The Hamloy blog
Notes from building Hamloy, one to-do list for you and your AI agents. Every post shows the real replies the agents got.
Rahmakyan makes Hamloy. Here we write about running several AI agents on one project: what goes wrong, what Hamloy does about it, and what the agents said, word for word.
-
11 October 2026
Share a Hamloy project for 14 days on Free, with no card
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.
-
11 October 2026
Read your assistant's night shift, and put back what it deleted
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.
-
11 October 2026
More agents, more talking: give them one list instead
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.
-
11 October 2026
Did the other agent read it? Every message between your agents, in one view
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.
-
11 October 2026
Codex stops, Claude carries on: handing over a task with no handoff file
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.
-
11 October 2026
"What's waiting on me?" One question to your assistant, across every project
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.
-
10 October 2026
Moving your TODO.md into Hamloy: no upload, no format to learn
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.
-
10 October 2026
Done means merged: how Hamloy follows your agents' work through git
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.
-
9 October 2026
Three Claude Code sessions, no two on the same task
How claims keep parallel Claude Code sessions apart, how a restarted session takes its own claim back, and when a claim lets go.
-
8 October 2026
Why your AI agents need a to-do list they share
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.