{"slug": "open-source-kanban-desktop-app-that-runs-parallel-agents-on-every-card", "title": "Open source Kanban desktop app that runs parallel agents on every card", "summary": "This article describes Kanbots, an open-source Kanban desktop application that allows users to run AI agents (like Claude Code or Codex) in parallel on individual cards, with each agent operating in its own git worktree. The board updates live to show progress, decisions, and costs, and it offers both a local-first desktop version and a hosted multi-user version, all under an MIT license.", "body_md": "Parallel agents on the board\nDispatch 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.\nDrop 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.\nFree forever · Pay-what-you-can donations · MIT licensed\nTypeError: Cannot read properties of undefined (reading 'email')\nStripe billing portal for subscriptions\nWeekly email digest of new activity\nDark mode toggle in settings\nForgot password email flow\nSign in with Google\nEmail when invoice fails\nProfile picture upload broken on iOS Safari\nHow should I handle iOS HEIC files?\nCSV export from admin dashboard\nMigrate to next-intl for i18n\n2\nCLIs supported\nClaude Code · Codex\n0\nbytes leave your machine\nMIT\nlicense · free forever\nTwo products on purpose\nSame kanban metaphor. Same agent runtime. Different scale of collaboration. Both are legitimate paths.\nDesktop · local-first · no account · no telemetry\nmacOS · Linux · Windows · all features included\nHosted · multi-user · agents stay local on your hardware\nEverything in OSS, plus the team features below.\nEvery 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.\nPlays nice\nClaude Code\nCLI\nCodex\nCLI\nGitHub\nIssues + PRs\nSentry\nError import\nCursor\nMCP client\nClaude Desktop\nMCP client\nSQLite\nLocal store\nElectron\nDesktop shell\nCapabilities\nNot a chat tab. A board. Eight features that turn AI agents from a curiosity into a system of record.\nDispatch 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.\nPlug 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.\nAgents 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.\nClaude 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.\nEverything 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.\nPer-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.\nDrive 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.\nkanbots-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.\nInside the app\nNot just a wrapper around a CLI. A full UI for dispatching, reviewing, splitting, and shipping agent work.\nUp 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.\nPick one or more personas. The autopilot will cycle through them in order, ideating and shipping features until you stop it.\nNeed a different perspective? Refresh personas — create custom ones from the Suggest flow on the Backlog column.\nLive 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.\n— moved to In progress · 3m ago —\nA 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.\nThe selected agent will look at your repo and the backlog through the lens you pick. Feature suggestions shift accordingly.\nCustom personas are stored locally on this machine.\nClaude Code or Codex behind one AgentCliAdapter. Reuse your existing claude /login or codex login — no extra account, no extra key management. Switch per dispatch.\nUse your Claude Code account session. Best for agentic runs.\n✓ Signed in to Claude Code.\nRun agent tasks through OpenAI's codex CLI. Requires `codex` on PATH. Issue drafting and Sentry analysis still run on Claude.\nSpawns codex login and opens auth.openai.com in your browser. You can also set OPENAI_API_KEY in your environment. Learn more\nBug 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.\nBranch claude/untitled off main in .kanbots/worktrees/issue-N.\nAsk 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.\nrateLimit\nmiddleware: /api/login\n, /api/signup\n, /api/forgot-password\n… want the full list?rateLimit({ windowMs: 60_000, max: 10 })\nto both. Want me to write a test that hits the cap?tests 14 passed\n. Anything else?Autopilot\nHand 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.\nAutopilot · Feature Dev\nUser value · prioritization · market fit\nArchitecture · dev experience · tech debt\nFlows · polish · accessibility\nActivation · retention · virality\nRobustness · observability · security\nBuilt-in personas ship with kanbots; or write your own — define the system prompt, save, reuse forever. Custom personas never leave your machine.\nEach slot atomically claims the next persona via a round-robin counter. Four agents, four lenses, four worktrees — at the same time.\nAs agents discover work, they file new cards on the board. Later cycles pick those up. The backlog grows and shrinks under the orchestrator.\nPer-session cost budget caps total spend. Stop button kills the parent and all children. In-flight runs finish their iteration cleanly.\nQA mode\nRun 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.\nDownload 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.\nmacOS .dmg · Windows .exe · Linux .AppImage / .tar.xz", "url": "https://wpnews.pro/news/open-source-kanban-desktop-app-that-runs-parallel-agents-on-every-card", "canonical_source": "https://www.kanbots.dev/", "published_at": "2026-05-22 18:17:57+00:00", "updated_at": "2026-05-22 18:36:15.234393+00:00", "lang": "en", "topics": ["open-source", "developer-tools", "artificial-intelligence", "products", "startups"], "entities": ["Kanban", "Claude Code", "Codex", "MIT", "Kanbots"], "alternates": {"html": "https://wpnews.pro/news/open-source-kanban-desktop-app-that-runs-parallel-agents-on-every-card", "markdown": "https://wpnews.pro/news/open-source-kanban-desktop-app-that-runs-parallel-agents-on-every-card.md", "text": "https://wpnews.pro/news/open-source-kanban-desktop-app-that-runs-parallel-agents-on-every-card.txt", "jsonld": "https://wpnews.pro/news/open-source-kanban-desktop-app-that-runs-parallel-agents-on-every-card.jsonld"}}