Skip to content
KAGAN logo

KAGAN

OpenCode plugin that runs agent tasks on a kanban board in separate git worktrees and merges nothing without your approval.

At a glanceswept 2026-10-10

≈ 3visits/mo

Emerging · estimate, read 2026-09-19

For
Developers building and supervising AI agents in their code editor
Activity
Maintainedrelease 3 months ago · site updated 7 months ago
Company
founding year not on record
What people do with itread off kagan.sh on 2026-09-26
  • supervise agentic development workflows
  • debug agent behavior in real-time
How a program reaches itfound, not claimed · read 2026-10-10
  • MCP serverio.github.kagan-sh/kaganpublished by kagan-sh on GitHub
  • Statenot asked yet

MCP server details →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Agentsby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

All Agents tools →

Questions this page answers
  • What is KAGAN?

    OpenCode plugin that runs agent tasks on a kanban board in separate git worktrees and merges nothing without your approval. It is listed in the Atlas under Agents.

  • Who is KAGAN for?

    Developers building and supervising AI agents in their code editor

  • Is KAGAN free?

    No. Its pricing page showed no free plan on 2026-09-26.

  • Do people use KAGAN?

    Emerging: ≈ 3 visits/mo · estimate, 2026-09 · 94 installs/mo (npm).

  • Is KAGAN still maintained?

    Maintained: release 3 months ago · site updated 7 months ago.

  • What are alternatives to KAGAN?

    In Agents, by use: Cloudflare, PolyAI, OpenClaw, BU, Tana, CrewAI.

Not quite it? Describe the job

beta

Five tools from the Atlas that fit it, each judged against what you wrote.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.