This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
ckanban
Hand your backlog to Claude Code. Come back to PRs.
A local kanban board for Claude Code. Move a ticket to Ready and a headless Claude Code session works it in its own copy of your folder, up to 5 at once. Claude plans with you first, a huddle of Claude reviewers checks risky work, then you review and merge. Runs on your own Claude plan, with no account and no cloud: everything stays in plain files on your Mac. Free and open source (MIT). macOS now, Linux next.
One night I left five tickets on my board and went to bed. By 3 AM all five were done: phone push notifications, ticket tags, a research report and two more, each waiting for my review.
That's ckanban: a kanban board on your Mac where every card is a Claude Code run. I'm Leo, I lead an AI agent team at respond.io, and I build ckanban with ckanban. Its own board has 265 tickets done in 5 weeks.
Move a card to Ready and a headless Claude Code session works it in its own copy of the folder, up to 5 at once. For risky work, a huddle of Claude teammates (reviewer, QA, security) argues over the change before it lands. 43 huddles have run on my board so far.
Why only Claude Code, not Codex? On purpose. Codex can create and steer tickets through MCP, but the runs are Claude Code only. That's what let me go deep: planning chats, huddles, follow-ups, auto-continue after a usage limit.
Honest limits:
macOS only. You need Claude Code, and runs use your own plan.
Claude runs commands in the ticket's folder without asking. Only add folders you trust it with.
What's the first ticket you'd leave running overnight? I'll read and reply to every comment today.
About ckanban on Product Hunt
“Hand your backlog to Claude Code. Come back to PRs.”
ckanban was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #97 on the daily leaderboard. A local kanban board for Claude Code. Move a ticket to Ready and a headless Claude Code session works it in its own copy of your folder, up to 5 at once. Claude plans with you first, a huddle of Claude reviewers checks risky work, then you review and merge. Runs on your own Claude plan, with no account and no cloud: everything stays in plain files on your Mac. Free and open source (MIT). macOS now, Linux next.
On the analytics side, ckanban competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how ckanban performed against the three products that launched closest to it on the same day.
Who hunted ckanban?
ckanban was hunted by Leo. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of ckanban including community comment highlights and product details, visit the product overview.
One night I left five tickets on my board and went to bed. By 3 AM all five were done: phone push notifications, ticket tags, a research report and two more, each waiting for my review.
That's ckanban: a kanban board on your Mac where every card is a Claude Code run. I'm Leo, I lead an AI agent team at respond.io, and I build ckanban with ckanban. Its own board has 265 tickets done in 5 weeks.
Move a card to Ready and a headless Claude Code session works it in its own copy of the folder, up to 5 at once. For risky work, a huddle of Claude teammates (reviewer, QA, security) argues over the change before it lands. 43 huddles have run on my board so far.
Why only Claude Code, not Codex? On purpose. Codex can create and steer tickets through MCP, but the runs are Claude Code only. That's what let me go deep: planning chats, huddles, follow-ups, auto-continue after a usage limit.
Honest limits:
macOS only. You need Claude Code, and runs use your own plan.
Claude runs commands in the ticket's folder without asking. Only add folders you trust it with.
Free, MIT, no account: github.com/leoawesome/ckanban
npx ckanban
What's the first ticket you'd leave running overnight? I'll read and reply to every comment today.