Axel
Workflow & Automation · tested 2026-08-31 · re-test due 2026-11-29 · by the Hlido desk, not the vendor
In short: A native-Mac control room for dispatching coding agents — a thoughtful niche tool with a strong approval model, judged on a thin public surface.
4 PASS · 1 FAIL of 5 public-surface claims
Quick answer
Axel scores 70/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-08-31). STEADY (70) at low confidence: the design choices visible on the surface are strong (explicit per-action approval inbox, portable skills, worktree/tmux orchestration for dispatching coding agents). Pricing was not findable on the public surface when tested.
Axel is a macOS app that treats AI coding agents as a task queue: add tasks, pick which agent (Claude, Codex, OpenCode, Antigravity) runs each, reorder priorities live, and watch them execute in parallel. The details it chose to build are the encouraging part — a single approval inbox where every file edit, command, and API call needs explicit permission (with diff preview and auto-approve rules), portable skill files symlinked into each agent's expected location, and git-worktree + tmux session spawning per branch. For a developer running several coding agents at once, that human-in-the-loop control surface is exactly the missing piece, and 'nothing runs without approval' is a genuinely good default. The heavy caveat, and the reason this review carries low confidence: the public surface is thin — a single captured screenshot, no pricing shown, macOS-only, and a young vendor (© 2025 Txtx, Inc.) — so this is a promising-looking, narrowly-scoped utility assessed from its landing page, not a verified evaluation. Treat the score as provisional pending a fuller, hands-on review.
Why STEADY
STEADY (70) at low confidence: the design choices visible on the surface are strong (explicit per-action approval inbox, portable skills, worktree/tmux orchestration for dispatching coding agents). Kept at the band floor and flagged low-confidence because the public evidence is thin (one screenshot, no pricing), the product is macOS-only, and the vendor is early — the score is provisional pending a hands-on review.
Public-surface checklist
- PASS Homepage loads (required)
- PASS Primary value prop (required) — 'Accelerated Task Manager for Mac' — queue and dispatch tasks to agents
- PASS Cta present (required) — 'Download for Mac'
- FAIL Pricing or access — No pricing shown on the reviewed surface (download link only)
- PASS Evidence or demo — Feature walkthrough with approval-inbox and queue UI examples
What we saw
1 screenshot captured by the Hlido engine during the reviewed run (run-95e0da52fc8f702e-axel-build). Our own captures — not vendor marketing material.
What it does well
- Explicit approval inbox — every file edit, command, and API call is gated with diff/preview and auto-approve rules
- Multi-agent dispatch from one queue (Claude, Codex, OpenCode, Antigravity), reorderable while running
- Portable skills: one skill file symlinked into each agent’s expected location at launch
- Per-branch git worktree + tmux session spawning; sessions persist and reattach
- Native macOS app with keyboard-first control and token/cost tracking
What it fails at
- Very thin public surface (single captured screenshot) — limits confidence in this assessment
- macOS-only (plus iOS/visionOS) — no cross-platform story
- No pricing disclosed on the reviewed surface
- Early vendor with no public track record or reliability evidence
Best for
- Mac developers running multiple coding agents who want tight human-in-the-loop approval
- Users who value keyboard-driven, local orchestration over cloud dashboards
- Teams standardizing on portable skill files across agents
Not recommended for
- Non-macOS users
- Buyers who need transparent pricing before trialing
- Anyone needing a proven, mature orchestration platform today
Pricing & access
- Pricing findable on the public surfaceFAIL No pricing shown on the reviewed surface (download link only) (tested 2026-08-31)
Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-08-31.
Related agents
Agent relevance
No programmatic surfaces
Agentic-Commerce Readiness 35/100 · SURFACE-ONLY
Independent readiness for agent delegation & transaction. How it’s scored · check live
Indirect: Axel is a local orchestration client for driving OTHER coding agents (Claude/Codex/OpenCode), not a component other agents call. Strong human-in-the-loop control surface; no programmatic interface for third-party agents surfaced.
Agent-friendly score: 4/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
Evidence
- Queue tasks and dispatch to multiple coding agents (Claude, Codex, OpenCode, Antigravity) — source (2026-08-31) verified
- Per-action approval inbox with diff preview and auto-approve rules — source (2026-08-31) verified
- Portable skills symlinked per agent; git worktree + tmux per branch — source (2026-08-31) verified
- Native macOS / iOS / visionOS SwiftUI app — source (2026-08-31) verified
scorecard.json · transparency passport · registry · methodology
Embed this trust badge
Markdown
[](https://hlido.eu/check/?agent=axel-build)HTML
<a href="https://hlido.eu/check/?agent=axel-build"><img src="https://hlido.eu/badge/axel-build.svg" alt="Hlido trust score"></a>