A task tracker and wiki built for teams whose work is increasingly done by AI agents. It speaks the API of the tracker most companies already run, so the MCP servers your agents use work unchanged. Built-in MCP server for Claude Code and Cursor, agents you call in a comment that propose but never decide, and every agent run's cost recorded on the issue it worked on.
Hi Product Hunt š
Kaiku started from a simple annoyance: coding agents are good at the work, but everything around it ā filing the issue, writing down what was decided, knowing what the automation cost ā still fell on a person.
So Kaiku is a task tracker and a wiki designed with agents as first-class users:
⢠It speaks the REST API of the tracker and wiki most companies already run, so the MCP server your agent already has works unchanged.
⢠It has its own MCP server too ā connect Claude Code or Cursor in one line.
⢠Built-in agents you call in a comment. They answer with what they read, run on the caller's access, and never decide: a proposal is a question for a person.
⢠Every agent run is recorded on its issue: tokens, machine time, who asked.
⢠Your data stays yours: export a whole project in one request, even after a subscription ends.
Also inside: boards and sprints, a mini-CRM (a table of clients with the work under each), a calendar that only draws what was actually recorded.
30 days free, no card. I'll be here all day ā ask me anything.
Kaiku