Aether Review 2026: Turn Your AI Subscription Into a Fleet of Devboxes
Aether (runaether.dev) turns the AI subscription you already pay for into parallel cloud devboxes where an agent streams every command, opens a PR, and another agent reviews and fixes it until the code holds up. We review the loop, the receipts, and the pricing.
You already pay for an AI subscription. Aether points it at a fleet of devboxes so one agent becomes many.
What is Aether?
Aether (runaether.dev) is a cloud devbox platform for AI agents. You delegate a task, fix, or review; an agent streams every command and diff live; it opens a pull request; and a second agent reviews, requests changes, and re-approves until the checks pass. Visual changes ship with a Playwright video, screenshots, and the full review thread as βreceipts.β
Key features
- Watchable loop: every command and diff streams as it lands; step in and take over at any point
- Plan mode: the agent proposes, you approve, then executes; queue follow-ups mid-run without restarting
- Agent-reviewed PRs: opened, reviewed, fixed, and re-reviewed until green
- Receipts: visual PRs include a Playwright video, screenshots, and the review thread
- Fleet: one subscription becomes parallel isolated devboxes running while you sleep
- Bring your own model: Aether bills only for compute; the LLM runs on the subscription you own
Who should use it?
Engineers who want to parallelize grunt work β fixes, reviews, dependency bumps β across isolated environments without paying twice for intelligence they already subscribe to.
Pros and cons
Pros: charges only for compute, not a second AI bill; truly interruptible; the review agent catches real regressions; visual receipts make UI review concrete; idle devboxes bill nothing.
Cons: tied to a supported AI subscription; free tier is thin (β4 hours/month); credit math needs planning for big jobs; early-stage pricing/SLA still settling; receipt reliability depends on the agent exercising the UI.
Pricing
Free tier (20 credits β 4 hours/month) plus Starter $30, Pro $75, Max $120 per month. 1 credit = 12 minutes on the default devbox; Medium 2x, Large 4x, XL 8x; idle bills nothing.
FAQ
Do I pay for the model twice? No β you bring the model via your existing subscription; Aether charges only for compute.
What are receipts? For PRs with visual changes, Aether attaches a Playwright video, screenshots, green checks, and the review thread so you can verify the change actually ran.
Explore the best AI Coding tools
Related Articles
agent-run Review 2026: Run Coding Agents in a Tiny Sandbox That Catches Mistakes Before They Spread
In-depth review of agent-run β a sub-1MB standalone binary that sandboxes coding agents (Claude Code, Codex, OpenCode, pi) inside a Bubblewrap container. Host filesystem is read-only by default. Built to catch agent mistakes, not malware.
Best AI Agent Tools in 2026: From Coding Assistants to Autonomous Workers
Complete guide to AI agent tools in 2026 β Claude Code, Codex, Cursor, Manus, and more. Which agents actually deliver on the promise of autonomous work?
Faultsense Review 2026: The expect() Without the Page
Faultsense is a zero-dependency browser agent that runs end-to-end assertions against real user sessions in production. We review how fs-* attributes work, RUM-style testing, and who should adopt it.
Best AI Coding Tools in 2026: Cursor vs GitHub Copilot
Compare the top 5 AI coding tools of 2026: Cursor, GitHub Copilot, Claude Code, v0, and Windsurf. Find the best AI pair programmer for your workflow.
Subscribe to the 9bests weekly β get the full list free
Hand-picked AI tool reviews and updates every week. Subscribe to receive this full list + 7 more quick-reference sheets (writing / image / video / audio / chat models / data / API cost).
Subscribe free & get it βIndependent reviews β ratings aren't influenced by vendor payments Β· double opt-in Β· unsubscribe anytime