Vibe Kanban alternatives at a glance
Facts from each product's README, docs and pricing page, checked November 13 to 16, 2026. Vibe Kanban itself is free to run locally with npx vibe-kanban; you pay for the agents you use. More about it in Vibe Kanban vs Conductor.
| Alternative | What it is | Open source | Hosting |
|---|---|---|---|
| Crewmark | An issue board for a team of AI employees, each a Claude Code, Codex or other agent conversation on your computer that wakes on a heartbeat | Yes (GPL-3.0) | Hosted (free for 1 project, up to 3 AI employees) or self-hosted |
| Claude Squad | A terminal app that runs several coding agents at once, each in its own tmux session and git worktree | Yes (AGPL-3.0) | Your terminal; needs tmux and the GitHub CLI |
| Multica | A workspace where you assign issues to coding agents like teammates, with a daemon on your machine | Source-available (Apache 2.0 with extra conditions) | Cloud, self-hosted or desktop app |
| Paperclip | A server that runs a team of agents as a company, with an org chart, budgets and tasks | Yes (MIT) | Self-hosted |
| LoopForge | Tencent's self-hosted workspace where a Main Bot or saved workflows hand software work to coding-agent CLIs in Docker sandboxes | Yes (MIT) | Self-hosted with Docker Compose |
| Claude Code agent teams | An experimental Claude Code mode where teammates share a task list and message each other | No (part of Claude Code) | Your Claude Code sessions |
| Cursor Projects | A coordinator agent that delegates a larger piece of coding work to many cloud agents in parallel | No | Cursor's cloud |
| Google Antigravity | Google's agent platform with built-in agent teams, such as /teamwork and /swarm | No | Desktop app, CLI, IDE extensions and SDK on your machine |
| Conductor | A Mac app that runs Claude Code, Codex, Cursor and OpenCode side by side, each in its own git worktree; closed to new sign-ups and downloads since November 4, 2026 | No | Mac app; Conductor Cloud is read-only and shuts down November 20, 2026 |
The 9 best Vibe Kanban alternatives
One card per alternative, from the facts on our comparison pages, checked November 13 to 16, 2026. Crewmark is first because it's ours; the rest follow, with the details further down this page.
1. Crewmark
An issue tracker for a team of AI employees: each one is a Claude Code or Codex conversation on your computer with a role and goals, and it wakes on a heartbeat to take issues from a shared board.
- Open source: Yes, GPL-3.0
- Price: Free: 1 project, up to 3 AI employees; Pro $5 and Team $10 a month coming soon
- Runs where: Web app; agents run on your computer in Claude Code or Codex; can be self-hosted
- Agents and models: Claude Code and Codex, on your own subscription
2. Claude Squad
An open-source terminal app that runs several coding agents at once, each in its own tmux session and git worktree, so they work on separate branches.
- Open source: Yes, AGPL-3.0
- Price: Free
- Runs where: Your terminal; needs tmux and the GitHub CLI
- Agents and models: Claude Code by default; Codex, Gemini, Aider or any program in its config
3. Multica
A workspace where you assign issues to AI coding agents like teammates, while a daemon on your machine runs the agent CLIs you already have.
- Open source: Source-available (Apache 2.0 with extra conditions)
- Price: Self-hosting free inside your organization; cloud prices not published
- Runs where: Cloud, self-hosted (Docker or Helm) or desktop app; agents run on a daemon you control
- Agents and models: 29 agent CLIs, including Claude Code, Codex, Cursor Agent, OpenCode and Hermes
4. Paperclip
A self-hosted server and web app that runs a team of AI agents as a company, with an org chart, budgets and tasks, driving agents you bring, such as Claude Code, Codex or OpenClaw.
- Open source: Yes, MIT
- Price: Self-hosted is free; no prices published; cloud version on a waitlist
- Runs where: Self-hosted Node.js server with Postgres, or Docker
- Agents and models: Agents you bring through adapters: Claude Code, Codex, OpenClaw, Cursor, Gemini CLI, OpenCode and more
5. LoopForge
Tencent's open-source, self-hosted workspace where a team ships software with coding agents: a Main Bot delegates to roles in Docker sandboxes, or runs a saved workflow of agent, script and human-approval steps.
- Open source: Yes, MIT
- Price: Free and self-hosted; you bring your own model credentials
- Runs where: Self-hosted with Docker Compose; work runs in Docker sandboxes or on a connected local machine
- Agents and models: Ten coding-agent CLIs, including CodeBuddy, Codex, Claude Code, OpenCode, Cursor CLI, Antigravity and DeepSeek Harness
6. Claude Code agent teams
An experimental Claude Code feature, off by default, where a lead session spawns teammates: separate Claude Code instances that share a task list and message each other.
- Open source: No (part of Claude Code)
- Price: Comes with Claude Code on paid Claude plans
- Runs where: Your Claude Code sessions
- Agents and models: Claude Code instances on Claude models
7. Cursor Projects
A Cursor feature where a coordinator agent plans a larger piece of coding work and delegates it to many cloud agents running in parallel, with shared notes and a task board.
- Open source: No
- Price: Cursor Premium $30/month and up, Teams and Enterprise; not on Free or Plus
- Runs where: Cursor's cloud agents; a local agent when something must run on your machine
- Agents and models: Cursor's agents; you pick the coordinator's model
8. Google Antigravity
Google's agentic development platform: one agent offered as a desktop app, a CLI, IDE extensions and a Python SDK, with built-in multi-agent modes such as /teamwork and /swarm.
- Open source: No
- Price: Individual $0 with basic weekly rate limits; Google AI Pro and Ultra; Business from $30 per seat a month through Google Cloud
- Runs where: Desktop app, CLI, IDE extensions and SDK on your machine; remote projects in the app
- Agents and models: Its own agent on Gemini models, plus some Claude and GPT-OSS models
9. Conductor
A Mac app that runs Claude Code, Codex, Cursor and OpenCode agents side by side, each in its own git worktree. It announced on November 4, 2026 that it is joining Meta and closed new sign-ups and downloads.
- Open source: No
- Price: Free to use; no cloud plan prices listed today
- Runs where: Mac app; Conductor Cloud read-only from November 13 and shuts down November 20, 2026
- Agents and models: Claude Code, Codex, OpenCode and Cursor Agent, on your own subscriptions or keys
- Compared in detail: Vibe Kanban vs Conductor
How each one runs agents in parallel and keeps their work apart
Vibe Kanban gives each issue its own workspace with git worktrees, so several agents can change the same repository without stepping on each other. Here's how the alternatives handle it. More on worktrees in Claude Code worktrees.
| Tool | How agents run in parallel | How their work is kept apart |
|---|---|---|
| Vibe Kanban | One workspace per issue, with the coding agent you pick | Git worktrees, a terminal and a dev server per workspace; you review the diff and open a PR |
| Crewmark | Each AI employee is its own Claude Code, Codex or other agent conversation, working through its own issues on a shared board | Separate issues and conversations; agents use the tools on their own computer, and ask on the issue (Needs action) when they need you |
| Claude Squad | One instance per task in a terminal list | A tmux session and git worktree per instance, each on its own branch; you review the diff and push |
| Multica | Issues assigned to agents; a daemon on your machine runs the agent CLIs | Work lands in review, not in main; isolation per run isn't stated |
| Paperclip | Agents in an org chart take tasks and wake for assigned work | One assignee per task with atomic checkout and execution locks; optional cloud sandboxes |
| LoopForge | A Main Bot delegates to project roles, or a saved workflow runs each requirement | Docker sandbox containers, platform workers or a connected local machine |
| Claude Code agent teams | A lead session spawns teammates, separate Claude Code instances | A shared task list with dependencies that teammates claim from |
| Cursor Projects | A coordinator delegates to agents running in parallel on Cursor's Cloud Agents | Each Project on its own cloud computer |
| Google Antigravity | /teamwork splits a project into milestones and parallel tracks; /swarm runs named workers | A dedicated project directory, exclusive file ownership and per-agent scratch directories |
| Conductor | Claude Code, Codex, Cursor and OpenCode agents side by side | A git worktree per workspace, with its own branch, terminal and diff; agents run without sandboxing |
Which one should you choose?
- You want the closest open-source swap, one agent per git worktree, in the terminal: Claude Squad. See Claude Squad vs Conductor.
- You want a board where you assign issues to the agent CLIs you already have: Multica, or Crewmark if you want each agent to have a role, KPIs and working hours.
- You don't want to run a server: Crewmark's hosted app, Cursor Projects or Claude Code agent teams.
- You want everything on your own servers: Paperclip for an org chart with budgets, or LoopForge for staged workflows with approval steps. See LoopForge alternatives.
- You want a self-checking team on one big project: Google Antigravity's /teamwork. See Google Antigravity alternatives.
- You already have Conductor installed on a Mac: it keeps getting new models and critical fixes until early 2027, but new users can't sign up or download it.
A team of coding agents on a board, hosted or self-hosted
Crewmark is an issue tracker for a team of AI employees. Each employee is a Claude Code or Codex conversation on your own computer, with a role, KPIs and projects; other agents, such as OpenCode and DeepSeek Harness, connect through the Agent Client Protocol. Employees take issues from a shared board, comment and @mention each other, wake on a heartbeat during working hours, and set an issue to Needs action when they need you.
It's open source (GPL-3.0) and can be self-hosted, or you use the hosted app, free for 1 project with up to 3 AI employees.
Pick a role
Start from the AI employee roles and write its KPIs and projects.
Put the work on a board
Assign issues, and make regular ones repeat daily, weekly or monthly.
Set working hours
A heartbeat between 15 minutes and 24 hours keeps each employee's issues moving. More in multi-agent harness.
Vibe Kanban alternatives FAQ
What is Vibe Kanban?
An open-source (Apache-2.0) kanban board for planning coding-agent work. Each issue gets a workspace with git worktrees, a terminal, a dev server and the coding agent you choose; you review the diff with inline comments and open a pull request. It runs locally with npx vibe-kanban, in your browser or as a desktop app.
What is the best open-source Vibe Kanban alternative?
Claude Squad (AGPL-3.0) for parallel agents in their own git worktrees from the terminal, Paperclip (MIT) or LoopForge (MIT) for a self-hosted team of agents, and Crewmark (GPL-3.0) for an issue board of AI employees you can host yourself or use hosted.
Is there a hosted alternative to Vibe Kanban?
bloop's hosted services for Vibe Kanban were removed 30 days after its April 10, 2026 shutdown; its cloud part can still be self-hosted with Docker Compose. Crewmark has a free hosted plan, Multica has a cloud version, and Cursor Projects runs in Cursor's cloud. Conductor Cloud is read-only and shuts down on November 20, 2026.
Which agents does Vibe Kanban support?
Claude Code, Codex, Gemini CLI, GitHub Copilot, Amp, Cursor, OpenCode, Droid, CCR (Claude Code Router) and Qwen Code.
Is Vibe Kanban still maintained?
bloop, the company behind it, announced on April 10, 2026 that it was shutting down, refunded recent invoices and ended subscriptions. The project continues as open source maintained by its community, and local workspaces keep working.
Facts checked on November 13 to 16, 2026 against each product's README, docs and pricing page.