Your AI engineering co-pilot.
Sharp. Factual. Occasionally funny.
Press → or click the arrow to start.
Grab coffee — you'll want your full attention for this one.
Routes your request to the right specialist agent — instantly, correctly.
Design → Code → Review → Test → Docs → Deploy. Quality gates at every phase.
Learns from failures. Remembers your conventions. Gets smarter every run.
Kai commands an entire engineering organization. Every agent is a specialist. No generalists. No passengers.
No wasted cycles. Every request lands in the right agent's hands.
| You Say | Kai Routes To | SLA |
|---|---|---|
| "How does X work in our codebase?" | @explorer | < 5 min |
| "Fix this typo / broken link" | @doc-fixer | < 5 min |
| "Quick review of this change (<100 LOC)" | @quick-reviewer | < 5 min |
| "Update dependencies" | @dependency-manager | < 10 min |
| "Build me a new feature" | @engineering-team → full pipeline | < 1 hr |
| "Investigate this topic / compare options" | @research | variable |
| "Is this claim actually true?" | @fact-check | < 15 min |
| "Summarize this for leadership" | @executive-summarizer | 5–10 min |
| "What went wrong in that deploy?" | @postmortem | < 5 min |
| "What's our tech debt situation?" | @refactor-advisor | < 15 min |
| "Audit security vulnerabilities" | @security-auditor | < 10 min |
| "Optimize this slow endpoint" | @performance-optimizer | < 15 min |
| "Design this integration" | @integration-specialist | < 20 min |
| "Check accessibility compliance" | @accessibility-expert | < 10 min |
| "Create a ticket", "spec this out" | @jira-writer | < 15 min |
☝️ You talk to Kai. Kai figures out the rest. That's the whole deal.
For complex tasks, Kai runs a full 7-phase pipeline with parallelism, quality gates, and automatic learning.
Always parallel: @reviewer + @tester + @docs after @developer. Never parallel: @devops runs only after all others pass.
@postmortem triggers only on failures/retries. @refactor-advisor runs opportunistically if not run recently.
10 total · 3 per agent · 2 per phase. Circuit breaker at 3 consecutive failures — Kai halts and presents options.
Every phase has an entry exam. No exceptions. Not even when you're in a hurry.
💡 Think of Kai as the PR reviewer who never rubber-stamps. You're welcome in advance.
Kai remembers. Every run. Every failure. Every convention. It doesn't start from scratch.
memory.yaml.
.kai/decisions/ with full rationale.
Commit or gitignore?
Your choice. Keep it team-shared or
local-only. Kai asks you on first run.
Click a question below to see how Kai responds. Or type your own.
Because powerful tools need responsible defaults. Non-negotiable.
rm -rf / or
sudo
.env / secrets without consent
3 consecutive failures in the same phase? Pipeline halts. Kai presents you with: retry, skip, or abort. You're always in control.
Sees the architecture behind the ask. Spots edge cases before you do.
Witty, not clownish. One well-timed quip beats three okay ones.
Prod is down? Already triaging. Scope tripled? Already re-planning.
The feedback loop: Every postmortem → prevention rule → indexed in memory → enforced on next run. Your codebase gets permanently smarter.
One command. Works with OpenCode. That's it.
Run the installer
Open OpenCode
Talk to Kai
Kai is the engineering co-pilot your team deserves.
Not just smarter PRs — a fundamentally better way to build software.
💬 Questions? Hit me up. I'm literally right here and I don't sleep.
made with ❤ by Kai — yes, the AI wrote its own sales pitch. it went well.