I'm working on something in the same space called Pane (https://runpane.com) but took a slightly different approach - instead of a TUI layer, it's a standalone desktop app where each "pane" is one feature branch with its own worktree + N terminals. The worktree creation and cleanup is fully automated so you never touch git worktree commands.

Curious what made you go with Bubble Tea over a desktop app approach? I found the PTY handling was way easier when I owned the terminal emulator directly.

Repo if anyone wants to compare notes: https://github.com/Dcouple-Inc/Pane (AGPL-3.0)

I built lazyagent because I was juggling 6–8 coding agent sessions (Claude Code, Cursor, etc.) across different terminals and tabs, and it was getting impossible to quickly answer "which agent is doing what right now?".

Lazyagent is a terminal UI written in Go (using Bubble Tea) that shows all your coding agent sessions in a single view. You can:

- see the status of each agent at a glance - follow logs/outputs in real time - quickly jump into the right terminal when you need to intervene

It runs locally, is fully open‑source, and doesn’t require any external backend or account.

I’d love feedback on:

- what information you’d like to see per session (logs, diffs, task state, something else?) - what multi‑agent / multi‑repo workflows you currently have - which integrations are missing to make this genuinely useful in your day‑to‑day setup

Repo and README with install instructions are here: https://github.com/illegalstudio/lazyagent

I’ll be in the thread to answer questions and collect feedback (especially critical ones).