AI coding agents are increasingly writing the world's code and human engineers now spend the majority of their time planning, reviewing, and orchestrating tasks. Vibe Kanban streamlines this process, enabling you to:
- Easily switch between different coding agents
- Orchestrate the execution of multiple coding agents in parallel or in sequence
- Quickly review work and start dev servers
- Track the status of tasks that your coding agents are working on
- Centralise configuration of coding agent MCP configs
- Open projects remotely via SSH when running Vibe Kanban on a remote server
You can watch a video overview here.
Make sure you have authenticated with your favourite coding agent. A full list of supported coding agents can be found in the docs. Then in your terminal run:
npx vibe-kanbanPlease head to the website for the latest documentation and user guides.
For developers working on the codebase, see the Architecture Documentation for detailed technical documentation including:
- Database Overview - Dual-database architecture (SQLite + PostgreSQL)
- SQLite Local Schema - Local node database schema
- PostgreSQL Hive Schema - Central hive database schema
- Database Synchronization - How data syncs between nodes and hive
We use GitHub Discussions for feature requests. Please open a discussion to create a feature request. For bugs please open an issue on this repo.
We would prefer that ideas and changes are first raised with the core team via GitHub Discussions or Discord, where we can discuss implementation details and alignment with the existing roadmap. Please do not open PRs without first discussing your proposal with the team.
Additional development tools:
cargo install cargo-watch
cargo install sqlx-cliInstall dependencies:
pnpm ipnpm run devThis will start the backend. A blank DB will be copied from the dev_assets_seed folder.
pnpm run stop # Stop instance for current directoryMulti-instance support
Vibe Kanban supports running multiple instances simultaneously (e.g., different projects). Each instance registers itself in /tmp/vibe-kanban/instances/ with:
- Project root directory
- Process ID (PID)
- All service ports (backend, frontend, MCP, hive)
This enables safe process management and helps executors discover which instance to connect to.
To build just the frontend:
cd frontend
pnpm build- Run
build-npm-package.sh - In the
npx-clifolder runnpm pack - You can run your build with
npx [GENERATED FILE].tgz
The following environment variables can be configured at build time or runtime:
| Variable | Type | Default | Description |
|---|---|---|---|
POSTHOG_API_KEY |
Build-time | Empty | PostHog analytics API key (disables analytics if empty) |
POSTHOG_API_ENDPOINT |
Build-time | Empty | PostHog analytics endpoint (disables analytics if empty) |
BACKEND_PORT |
Runtime | 0 (auto-assign) |
Backend server port |
FRONTEND_PORT |
Runtime | 3000 |
Frontend development server port |
HOST |
Runtime | 127.0.0.1 |
Backend server host. Set to 0.0.0.0 for network access |
DISABLE_WORKTREE_ORPHAN_CLEANUP |
Runtime | Not set | Disable git worktree cleanup (for debugging) |
Connect your local Vibe Kanban instance to a central hive server for distributed task management:
| Variable | Required | Description |
|---|---|---|
VK_HIVE_URL |
Yes | WebSocket URL of the hive server (e.g., wss://hive.example.com) |
VK_NODE_API_KEY |
Yes | API key for authenticating with the hive |
VK_NODE_NAME |
No | Human-readable name for this node (defaults to hostname) |
VK_NODE_PUBLIC_URL |
No | Public URL for direct log streaming (e.g., http://192.168.1.50:3000) |
VK_CONNECTION_TOKEN_SECRET |
No | JWT secret for validating direct connection tokens |
See docs/swarm-hive-setup.mdx for the complete setup guide.
Build-time variables must be set when running pnpm run build. Runtime variables are read when the application starts.
Vibe Kanban supports a distributed swarm architecture where multiple local nodes connect to a central hive server:
┌─────────────────────────────────────────────────────────────────┐
│ HIVE (Remote Server) │
│ PostgreSQL + Activity Broker + Node Registry │
└──────────────────────────┬──────────────────────────────────────┘
│ WebSocket (persistent)
┌────────────────┼────────────────┐
│ │ │
▼ ▼ ▼
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ NODE: Mac │ │ NODE: Linux │ │ NODE: Windows │
│ (local srv) │ │ (local srv) │ │ (local srv) │
└─────────────────┘ └─────────────────┘ └─────────────────┘
Features:
- Centralized management of projects and tasks across multiple machines
- Remote task execution with live log streaming
- Direct node connections for low-latency logs, with hive relay fallback
- Cross-platform support (macOS, Linux, Windows)
Quick Start:
# On each node, set environment variables and start
export VK_HIVE_URL=wss://hive.example.com
export VK_NODE_API_KEY=your-api-key
pnpm run devSee docs/swarm-hive-setup.mdx for detailed instructions.
When running Vibe Kanban on a remote server (e.g., via systemctl, Docker, or cloud hosting), you can configure your editor to open projects via SSH:
- Access via tunnel: Use Cloudflare Tunnel, ngrok, or similar to expose the web UI
- Configure remote SSH in Settings → Editor Integration:
- Set Remote SSH Host to your server hostname or IP
- Set Remote SSH User to your SSH username (optional)
- Prerequisites:
- SSH access from your local machine to the remote server
- SSH keys configured (passwordless authentication)
- VSCode Remote-SSH extension
When configured, the "Open in VSCode" buttons will generate URLs like vscode://vscode-remote/ssh-remote+user@host/path that open your local editor and connect to the remote server.