I just shipped v1.1.0 of oh-my-kimi — a multi-agent orchestration harness that wraps the Kimi Code CLI (K2.6) into parallel coding teams.

What it does

One prompt → planned, parallelized, reviewed project:

npm install -g @oh-my-kimi/cli
omk init
omk run "Build a Next.js landing page with dark mode and contact form"

v1.1.0 highlights

• omk chat — Interactive Kimi session with resumable context, tmux support
• omk cockpit — Real-time dashboard with parallel TODO/agent rendering
• omk hud — Full terminal dashboard with goal scoring and ETA estimation
• DAG scheduler — Retry, skip-on-failure, fallback roles, evidence gates
• Parallel agents in git worktrees — Agents don't step on each other
• Live quality gates — lint, typecheck, test, build enforced before completion
• Local graph memory — Optional Neo4j/Kuzu backends
• 234 tests passing, CI green

Why

Most CLI coding agents run single-threaded — one agent, one task. I wanted dependency-aware parallel execution where agents work in isolated git worktrees and merge cleanly.

Links

• GitHub: https://github.com/dmae97/oh-my-kimi
• npm: https://www.npmjs.com/package/@oh-my-kimi/cli
• MIT license, Node 20+, requires Kimi API key

OMK one prompt landing page