Launching today
Axel

Axel

Todoist for AI coding agents

178 followers

Axel helps you run AI agents and keep them fed. Queue up work, dispatch to the right agent, and approve or deny actions from one inbox. It's native macOS, keyboard-driven, and works with Claude, Codex, OpenCode, and Antigravity out of the box. We hope it helps you ship faster πŸš€
Axel gallery image
Axel gallery image
Axel gallery image
Free
Launch Team
Webflow | AI site builder
Webflow | AI site builder
Start fast. Build right.
Promoted

What do you think? …

fmerian
Hunter
πŸ“Œ

@Axel is a beautifully-crafted task manager for AI coding agents. Native for macOS and built for speed (read: keyboard-driven), Axel works with Claude, Codex, OpenCode, and Antigravity out of the box.

If you're working with multiple coding agents, this might be your new favorite tool.

Oh and it's open-source: View source code

Happy shipping!

Ludo Galabru

Thank you @fmerian πŸ™
Hey PH β€” I'm Ludo, the author of Axel, and I'm a todo list junkie. I've literally tried them all.

Coding agents are redefining my day-to-day work. I have a few years of devtool experience, so I started exploring a developer experience where my interactions are led by a list of tasks β€” tasks that can be chained, prioritized, and processed by agents I choose.

Not an agent that happens to have a task list. A task list that happens to command agents.

The workflow I was after: queue up what needs to happen, pick which agents handle what, parallelize across git worktrees so nothing collides, and keep one calm interface while the machine goes to war underneath.

That's Axel β€” a native macOS app that gives you the calm of a task list while your agents are in war mode. Spinning up another agent in its own worktree feels as cheap as opening a new tab.

The app is built with SwiftUI, inspired by Things. Under the hood it leans on GhosttyKit, tmux, and OpenTelemetry to run and monitor the agents being spun up.

Axel is early but it's already part of my daily flow, and that's usually when I know something's worth sharing. I'd love honest feedback, good or bad! Tell me what clicks and what doesn't.

fmerian
Hunter

@ludovicΒ lfg! keep up the great work

Gokul Chandrasekaran

One of the hurdles I have is waiting for the task to finish to start next or work on two different projects. This seems to solve that. Good work.

Ludo Galabru
@gokuljd I’m with you! with the Alex flow, I create my tasks, queue them, create new ones, get back to editing some that have been queued, etc.
fmerian
Hunter

@gokuljdΒ spot on! curious: what are your preferred coding agents?

Ludo Galabru
@fmerian It’s a mix, I usually dispatch my tasks to Claude, and get some backup from Codex. The good thing is that with that flow, it’s really easy to benchmark the quality.
Mykola Kondratiuk

been running Claude Code and Cursor side by side for months, biggest pain is when they both want to touch the same file. the worktree approach is smart - does each agent get its own isolated git state or do they somehow sync changes back? also curious how you're handling permissions, like can agents accidentally blow away each others work or is there some kind of conflict detection built in?

Ludo Galabru
@mykola_kondratiuk good question. When you start parallelizing agents, then the current challenge I see (will probably fade out with support from AI over time too) is 1) dispatch the work correctly (includes avoiding conflicts) 2) review the work done. Axel spins up git worktrees + tmux sessions under the hood which creates some good isolation. The permission issues you’ve mentioned is fixed by the combo OpenTelemetry listener + native app, that gives you rich notifications (ability to approve decline changes, access, etc)
Piroune Balachandran

Worktree isolation is the easy win. The part that gets ugly is when three agents touch overlapping files and you're stuck resolving merge conflicts after the fact. Axel piping OTel into native macOS notifications is a nice touch... most tmux setups just dump to stdout and you miss the signal in the noise.

Wilco Kruijer

Seems interesting. What is a typical workflow with Axel? Would I be creating multiple tasks which are then spread over multiple agents? Or is it more a 1:1 workflow where I'm "baby sitting" an agent?

fmerian
Hunter

What is a typical workflow with Axel? Would I be creating multiple tasks which are then spread over multiple agents?

Exactly. How @Axel works:

  1. You create a task in the app.

  2. Axel spawns a terminal session via the CLI.

  3. The agent runs in tmux, optionally inside a new git worktree.

  4. The app shows live output, events, and permission prompts.

  5. When the work is done, you close the loop and ship.

Adam Lababidi

Using git worktrees for agent isolation is genius - makes spawning agents "as cheap as opening a tab."

How do you handle the merge back to main when two agents touch related files? Does OpenTelemetry help detect potential conflicts before merge?

Love the Things-inspired UI approach!

fmerian
Hunter

Using git worktrees for agent isolation is genius (...) Love the Things-inspired UI approach!

@ludovic frame this!

Prakash

It gives a clear picture of what's going on, I love that you support different agents.

a lot more agents are coming very soon.

fmerian
Hunter

@prakashqbtrixΒ love it! what model should they support next? any preferences? feel free to create an issue in: https://github.com/txtx/axel-app

Bill Chirico
Why not just use Todoist API?
12
Next
Last