Axel
Todoist for AI coding agents
FreeCLIOpen SourceAI8,766 impressions#2 of its week2 comments
Comments
>log in to comment- PDFops· 3mo ago
The single-inbox approve/deny is the right primitive — the moment you run more than two agents, the bottleneck stops being the agents and becomes you context-switching between their approval prompts. Pulling them into one keyboard-driven queue is exactly the fix. The thing I'd want next is a graduation path off per-action approval: once an agent has done the same safe action twenty times, approving the twenty-first by hand is just tax. Some notion of "auto-approve this class of action for this agent, still log it" is where the inbox model really pays off — you keep the audit trail without staying the human bottleneck forever.
- Zain Sheikh· 3mo ago
Approving or denying agent actions from one inbox is the piece I keep missing when I have a few agents running at once, and keeping it native and keyboard-driven fits that workflow well. Any plans for a Linux build?
Axel is a native macOS task manager that queues, dispatches, and approves AI coding agents.
- for
- Developers who use AI agents for code generation and automation on macOS.
- license
- open source
- cli-v0.8.07 months ago
Key features
- Task Queue — Add, reorder, and prioritize tasks for multiple agents that run in parallel.
- Agent Dispatch — Select which AI model (Claude, Codex, OpenCode, Antigravity) executes each task.
- Inbox Approval — Approve or deny file edits, commands, and API calls from a single inbox with full context.
- Skill Files — Define reusable agent skills in a single YAML/markdown file synced to each agent.
- Token & Cost Tracking — View input/output token counts and USD cost per task and per session.
- Native macOS Integration — SwiftUI app with menu bar, keyboard shortcuts, Spotlight search, and macOS/iOS/visionOS support.
Use cases
- Queue a series of code refactoring tasks and let Claude handle them while you monitor progress.
- Approve a security-sensitive file edit requested by an AI agent before it is applied.
- Run automated test suites via an AI agent and see token usage and cost in real time.
- Switch between Codex and OpenCode for different parts of a project without restarting the tool.
Axel vs alternatives
| Axel |  Fine |  BuildShip |  SuperAGI Cloud |  Pocketenv | |
|---|---|---|---|---|---|
| Best for | Keyboard-driven AI agent task management | AI-driven code generation platform | Visual AI backend construction | Cloud-hosted autonomous AI agents | Universal sandbox runtime |
| Pricing | Free | Free | Free | Free | Free |
| DevHunt upvotes | 7 | 75 | 118 | 43 | 73 |
| Launched | Jul 2026 | Jan 2023 | Jan 2023 | Jan 2023 | Apr 2026 |
- Axel vs Fine: Fine focuses on building software with AI agents but lacks a native macOS task-queue UI.
- Axel vs BuildShip: BuildShip provides a visual drag-and-drop backend builder, not a keyboard-centric agent queue.
- Axel vs SuperAGI Cloud: SuperAGI Cloud runs autonomous agents in the cloud, whereas Axel runs locally on macOS.
- Axel vs Pocketenv: Pocketenv offers sandbox runtimes for agents and humans, not a task-management inbox.
Axel FAQ
How do I choose which AI agent runs a task?+
When adding a task you can select the desired agent (Claude, Codex, OpenCode, or Antigravity) from a dropdown before dispatch.
Can tasks be reordered while they are running?+
Yes, you can drag to reorder or change priorities on the fly without restarting the agents.
What happens if an agent wants to edit a file?+
The request appears in the inbox with a diff preview; you must approve, deny, or set an auto-approve rule.
Do I need to use the mouse to operate Axel?+
No, all actions—including creating panes, dispatching tasks, reordering, and killing agents—are available via keyboard shortcuts.
How does Axel track usage costs?+
It shows input/output token counts and calculates the USD cost per task and cumulative totals for the session.
Summarized by DevHunt from axel.build · Sep 29, 2026. Details may change; check the official site.
