# Open source Kanban desktop app that runs parallel agents on every card

> Source: <https://www.kanbots.dev/>
> Published: 2026-05-22 18:17:57+00:00

Parallel agents on the board
Dispatch on as many cards as you want; each agent runs in its own git worktree on a kanbots/issue-N branch. The board updates live as runs progress, decisions surface, costs accrue.
Drop a folder. Get a board. Dispatch Claude Code or Codex agents on as many cards as you want — each in its own worktree. Or hit autopilot and let personas split the work, run in parallel, and check their own output while you sleep.
Free forever · Pay-what-you-can donations · MIT licensed
TypeError: Cannot read properties of undefined (reading 'email')
Stripe billing portal for subscriptions
Weekly email digest of new activity
Dark mode toggle in settings
Forgot password email flow
Sign in with Google
Email when invoice fails
Profile picture upload broken on iOS Safari
How should I handle iOS HEIC files?
CSV export from admin dashboard
Migrate to next-intl for i18n
2
CLIs supported
Claude Code · Codex
0
bytes leave your machine
MIT
license · free forever
Two products on purpose
Same kanban metaphor. Same agent runtime. Different scale of collaboration. Both are legitimate paths.
Desktop · local-first · no account · no telemetry
macOS · Linux · Windows · all features included
Hosted · multi-user · agents stay local on your hardware
Everything in OSS, plus the team features below.
Every Cloud-only feature requires either another person or another devicein the picture. None of them help a solo user on one machine — so we don't gate them. OSS is what one person does on their machine; Cloud is what a team does together.
Plays nice
Claude Code
CLI
Codex
CLI
GitHub
Issues + PRs
Sentry
Error import
Cursor
MCP client
Claude Desktop
MCP client
SQLite
Local store
Electron
Desktop shell
Capabilities
Not a chat tab. A board. Eight features that turn AI agents from a curiosity into a system of record.
Dispatch on as many cards as you want; each agent runs in its own git worktree on a kanbots/issue-N branch. The board updates live as runs progress, decisions surface, costs accrue.
Plug in personas — product, engineer, reviewer, tester — and a parallelism count up to 4. The orchestrator round-robins through personas, splits parent issues into subtasks, and evolves the backlog as agents discover work. Personas spawn personas.
Agents pause and ask. You click an option; the run continues. Numbered shortcuts, edit-and-resubmit, slash commands like /spec, /review, /split. Reviewable decisions, not silent tree mutations.
Claude Code or Codex. Same board, same worktrees, same decision UI — kanbots speaks both stream formats behind a single AgentCliAdapter. Use your existing claude /login or OPENAI_API_KEY.
Everything lives in .kanbots/ next to your repo: SQLite database, configs, worktrees. No cloud account, no telemetry, no HTTP server. Your code never leaves the machine.
Per-run, per-card, per-project rollups. Watch the cost meter accrue as agents work. Set per-run and per-session caps; runs stop on cost-budget. No surprise bills.
Drive real GitHub issues with your personal PAT. Promote a worktree to a commit, or open a draft PR with one click. A pre-push hook means agents never publish on their own.
kanbots-mcp-server exposes the board over the Model Context Protocol so Cursor, Claude Desktop, or anything MCP-aware can drive it. The board becomes a first-class tool for your other agents.
Inside the app
Not just a wrapper around a CLI. A full UI for dispatching, reviewing, splitting, and shipping agent work.
Up to 4 parallel slots round-robin through your roster. Each slot atomically claims the next persona; agents split parents into subtasks as they go. Stops on completion or session budget.
Pick one or more personas. The autopilot will cycle through them in order, ideating and shipping features until you stop it.
Need a different perspective? Refresh personas — create custom ones from the Suggest flow on the Backlog column.
Live thread streams every tool_use and tool_result. When the agent needs a call, the run pauses with numbered options. Reply box accepts slash commands: /spec, /review, /split.
— moved to In progress · 3m ago —
A persona is a named system prompt snippet. Built-ins ship with the app; New persona lets you write your own — save, reuse forever. Custom personas stay on your machine.
The selected agent will look at your repo and the backlog through the lens you pick. Feature suggestions shift accordingly.
Custom personas are stored locally on this machine.
Claude Code or Codex behind one AgentCliAdapter. Reuse your existing claude /login or codex login — no extra account, no extra key management. Switch per dispatch.
Use your Claude Code account session. Best for agentic runs.
✓ Signed in to Claude Code.
Run agent tasks through OpenAI's codex CLI. Requires `codex` on PATH. Issue drafting and Sentry analysis still run on Claude.
Spawns codex login and opens auth.openai.com in your browser. You can also set OPENAI_API_KEY in your environment. Learn more
Bug fix · Feature · Refactor · Review · Spike templates. Three start modes: spec-first (run /spec, await approval), create-and-dispatch, or queue-for-later. Title becomes branch + PR title.
Branch claude/untitled off main in .kanbots/worktrees/issue-N.
Ask anything — "which routes don't have rate limiting?", "where do we use the old auth helper?". A general-purpose agent that knows your repo, your tests, and your git state.
rateLimit
middleware: /api/login
, /api/signup
, /api/forgot-password
… want the full list?rateLimit({ windowMs: 60_000, max: 10 })
to both. Want me to write a test that hits the cap?tests 14 passed
. Anything else?Autopilot
Hand kanbots an issue and a budget. The orchestrator round-robins through a roster of personas, runs up to four slots in parallel, splits parent issues into subtasks, and keeps cycling until the work converges or the cost cap hits.
Autopilot · Feature Dev
User value · prioritization · market fit
Architecture · dev experience · tech debt
Flows · polish · accessibility
Activation · retention · virality
Robustness · observability · security
Built-in personas ship with kanbots; or write your own — define the system prompt, save, reuse forever. Custom personas never leave your machine.
Each slot atomically claims the next persona via a round-robin counter. Four agents, four lenses, four worktrees — at the same time.
As agents discover work, they file new cards on the board. Later cycles pick those up. The backlog grows and shrinks under the orchestrator.
Per-session cost budget caps total spend. Stop button kills the parent and all children. In-flight runs finish their iteration cleanly.
QA mode
Run typecheck / tests / lint / build / e2e in the worktree. Optionally start your dev server and watch it. For every failing check, dispatch a fix run on a derived child issue. Repeat until green.
Download the OSS desktop app today and put every agent run on a kanban — visible, decisioned, contained. When your team needs to share a board, cloud is one upload away.
macOS .dmg · Windows .exe · Linux .AppImage / .tar.xz