Discover

Kaiku

A task tracker and wiki where AI agents work as part of the team
7 ratings4.37
Saves78
CategoryProductivity
PlatformWeb
PricingFreemium

Kaiku is an AI-agent-native task tracker and wiki designed for teams integrating AI assistants. It supports issue tracking, comments, and wikis compatible with existing MCP APIs, records agent runs and their costs, and offers built-in AI agents that propose solutions needing human approval. It also includes a mini-CRM feature and supports importing projects from popular task managers.

automation

Ratings & Reviews

Write a review
4.37

7 reviews

Product
4.87
Design & Polish
3.87
Performance
4.37
Mobile PageSpeed
Performance
82 out of 100, Needs improvement
Accessibility
96 out of 100, Good
Best Practices
100 out of 100, Good
SEO
100 out of 100, Good

Be the first to share a thoughtful review.

Information

CategoryProductivity
PlatformsWeb
PricingFreemium
AccountSign-in detected
ListedSeptember 2026
Report a problem

Website checks

Mobile PageSpeed
Performance
82 out of 100, Needs improvement
Accessibility
96 out of 100, Good
Best Practices
100 out of 100, Good
SEO
100 out of 100, Good

Around the Web

Product Hunt78 source points · 2 comments

The cost-on-the-issue part is what I'd want most. I run a bunch of scheduled agent jobs for a small job board (posting, moderation, a daily article), and the expensive surprises were never one big run, they were duplicates. My laptop slept through a few slots, the scheduler caught up on wake and the same job ran twice, so two identical posts went out and nobody noticed until a reader did. What fixed it was boring: each job reads a small log of what it already did today before touching anything. If an agent picks up the same Kaiku issue twice after a retry, does the second run see the first one's record and stop, or does it just log a second cost line next to it?

antonkylikov · Imported from Product Hunt