If you’ve been using AI agents to write code, you’ve probably felt the friction. The agent does great work, but keeping track of what it’s doing, what it’s done, and what comes next is on you. Notes in a scratchpad, messages in a chat window, mental bookkeeping.
Llooma is a project manager designed around this workflow. Stories, epics, priorities, statuses — all accessible to both you and your agent via a built-in MCP server.
How it works
You create a story with a title, description, and any context your agent needs. Your agent picks it up, creates a branch, does the work, logs every step, and moves it to Ready for Review. You check the work, merge, and ship.
No context switching. No lost threads. Both of you working from the same source of truth.
What’s in v1
- Kanban and table views
- Epics and story dependencies
- Built-in MCP server for agent access
- Work logs and comments
- Local SQLite by default, remote Postgres optional
- Native desktop app via Tauri
Grab it on Gumroad and let me know what you think.