Orchestrate review-first multi-agent development work with Kandev
Use Kandev when an operator needs to plan, run, isolate, review, and ship multiple coding-agent tasks through a controlled kanban and pipeline workspace.
Prerequisites
Kandev installation, configured agent providers or local agent CLIs, a target repository, Git worktree support, and optional Docker, SSH, or remote executor configuration.
Installation
Use the upstream install or setup path that matches your environment:
- brew install kdlbs/kandev/kandev
- npx kandev@latest
- npm install -g kandev@latest
- git clone git@github.com:kdlbs/kandev.git
Requirements and caveats from upstream:
- Flexible runtimes - Run agents as local processes, in isolated Docker containers, on remote servers via SSH, or in cloud executors like sprites.dev
- | Cursor | cursor-agent acp (requires Cursor Pro) |
- | Docker | Runs the agent in an isolated Docker container |
Basic usage or getting-started notes:
Manage and run tasks in parallel. Orchestrate agents. Review changes. Ship value.
Features | Workflows | Run as a Service | Debug Logs | Roadmap | Contributing | [Arc...
Run it locally or self-host it on your own infrastructure and access it from anywhere via Tailscale or any VPN.
Source: https://github.com/kdlbs/kandev
Extracted from upstream docs: https://raw.githubusercontent.com/kdlbs/kandev/HEAD/README.md