Lukan is an open-source AI workstation that runs on top of your operating system to complete real end-to-end work. It includes an integrated coding agent that can read and edit files, run terminal commands, and automate technical tasks. Its terminals are tmux-based for persistent sessions, and you can run multiple agents either directly in terminal panes or through the agent UI. You can also create agentic pipelines to automate multi-step workflows with approvals and notifications.
Hey PH 👋
I built Lukan because my workflow changed a lot in the last year.
Now I’m coding with AI, managing tasks with AI, and shipping products with AI, but everything was spread across too many tools. I wanted one place to run and orchestrate agents, see what they’re doing, and switch between private and open-source models without the usual chaos.
Lukan includes OpenClaw-style channel support, so you can control agents from WhatsApp, Telegram, and Slack.
It also ships with an integrated coding agent (Claude Code-style), built in Rust.
I also left a relay binary and code in repo for remote access: deploy it on a VM or container and expose it to the internet. You can also use a Cloudflare Tunnel on port 3000 (or any port you configure).
Lukan has both skills and plugins:
Skills are compatible with markdown-style workflows used by coding agents.
Plugins give tighter, safer control for integrations where “just prompt it” isn’t enough.
It’s still early, but already very useful in my day-to-day work, and I wanted to share it now so we can improve it with the community.
Install is simple: just type lukan in your terminal and follow the steps.
Would love your feedback ❤️
the pipeline approvals layer - is it blocking or async? curious how you handle failure recovery when an agent step needs human input but the user is offline
