Aether

brew install , then aether run streams a cloud task into your prompt. Tasks, files, git, secrets, and billing are all commands, and the whole devbox is one aether ws ssh away. zsh · your machine $ brew install Aether-Runtime/aether/aether $ aether run "fix the flaky auth test" → devbox ready in 4.7s ▸ FAIL auth.test.ts reproduced ▸ pinned the order-dependent assertion ▸ 8/8 passing · pushing fix ▸ PR #1848 opened · checks running REST & WebSocket API Everything on this page is scriptable: a REST API with platform keys for projects, tasks, and automations, plus a WebSocket feed of the live workspace, terminal to git. 1 curl -X POST api.runaether.dev/v1/tasks \ 2 -H "Authorization: Bearer aether_..." \ 3 -d '{ 4 "prompt": "fix the flaky auth test", 5 "project_id": "defce268" 6 }' 202 { "id": "d2b62f2d", "status": "queued" } ws → task.status: running ws → terminal: npm test ✓ Skills from your repo Commit a SKILL.md and every agent that touches the repo follows it: your test conventions, your review bar, your deploy rules. Personal skills follow you across projects. acme-checkout/ └─ .agents/skills/ ├─ webhook-testing/ SKILL.md └─ release-checklist/ skill.md Always test duplicate delivery: call the handler twice with the same event… ▸ loaded into every agent session on this repo Live port previews Every port the agent opens gets its own URL. Click into the running app and test it like localhost, hot reload included, or hand the link to a teammate. Private by default. ⚿ 5173-acme.preview.runaether.dev $149.00 $28.00 Total $177.00 Pay now 5173 web · live 4000 api 5432 db ⚡ hot reload Video proof on PRs The agent has a real browser on a real display. It clicks through what it built, records the session, and embeds the MP4 and before/after screenshots in the PR description. ▶ 0:42 checkout-retry.mp4 embedded in PR #1848 before .png after .png diff .png Bring any model Claude Code, Codex, or OpenCode, on your own subscription, with 40+ models behind them. Pick the model and reasoning effort per task. agent · model · effort claude code claude-sonnet-5 ✓ low med high max claude-fable-5 codex gpt-5.5 · xhigh opencode · openrouter kimi-k2, deepseek-v4, +40 more ✓ your keys, your choice, per task Terminal Slack Linear API zsh · your machine aether $ brew install Aether-Runtime/aether/aether $ aether run "fix the flaky auth test" → devbox ready in 4.7s ▸ FAIL auth.test.ts reproduced ▸ fix pushed, opening PR #1848 Start tasks where you already work. brew install the CLI and aether run streams a cloud task into your prompt. Mention Aether in Slack, assign it a Linear issue, or hit the API with a platform key: every surface reaches the same loop. Oversight A loop you can watch and take over. The whole devbox is open while the loop runs: terminal, file editor, port previews, Docker. Watch every command live. Jump in mid-run, type in the same terminal, steer, or take the wheel entirely. Autonomy that never asks for blind trust. Plan mode: the agent proposes, you approve, then it executes Queue follow-ups mid-run and the agent folds them in without restarting Stop the agent anytime and the devbox stays alive, yours to use Demo: while an agent streams commands in the devbox terminal, a human clicks in and types a command; the agent pauses, a chip flips to "you're driving," then control hands back. acme-checkout agent/1863 ● checks pending Watch · Steer · Take over webhooks/checkout.ts export async function handleRetry ( event ) { const charge = await findCharge ( event ) if ( charge . status === 'succeeded' ) return return recharge ( event ) } terminal agent driving you're driving ▸ applying idempotency guard… ▸ npm test: running 8 specs $ git diff --stat checkout.ts | 14 ++ -- checkout.test.ts | 9 ++ 2 files changed, 20 insertions(+), 3 deletions(−) ▸ resuming: 8/8 specs green AI that never ships its first draft. Shipped by an agent. Reviewed by an agent. Approved by you. Turn on Aether review and every PR the agent opens runs a gauntlet before it reaches you: a review agent tears the diff apart in GitHub, the author fixes and pushes, and the review runs again until the code holds up. What lands in your repo has already survived review, with a video to prove it works. Recorded live, unedited: the reviewer traced a double-charge bug through the callers, the author fixed it, and the loop converged in 12 minutes. No human touched it. Read the real PR this loop shipped → Demo: Aether opens a pull request, its review agent finds a double-charge bug and requests changes, the author agent pushes a fix, the review approves, and the pull request resolves with passing checks and a demo video. Recorded live · unedited Seeing is shipping. Every PR making visual changes arrives with the receipts: a Playwright video of the change actually running, screenshots, green checks, and the full review thread. playwright · checkout-retry.mp4 0:42 ✓ 8 checks passing 3 screenshots +18 −3 aether review approved Idempotency guard verified against the duplicate-delivery test. Approving. ✓ Your subscription, multiplied. You already pay for Claude Code, Codex, or OpenCode. On your laptop that buys one agent, one task, your attention, your battery. Point the same subscription at Aether and it becomes a fleet: parallel isolated devboxes, each ready in seconds, running while you sleep, wired into GitHub, Slack, Linear, and Sentry. The model is yours. We're everything around it. 1 agent · your machine fix: flaky auth test feat: export CSV 3:12 AM fix: sentry #4231 fix: merge conflict feat: paginate logs fix: failing CI Don't pay for intelligence twice. Black-box agents rent you a model at a markup and hide it inside an opaque meter. Aether charges only for compute: the intelligence runs on the subscription you already own. A month of agent work elsewhere $80/mo + $40 per dev seat VM time bundled model inference bundled, marked up networking bundled opaque meter, can't pause mid-task The same month on Aether Pro $75/mo compute metered, visible model inference $0 to us (your own subscription) idle time 0 credits per-second billing Comparison uses list pricing for the leading black-box agent as of July 4, 2026. Free $0 20 credits a month Kick the tires on real tasks. Start free 1 warm slot — instant starts Small & Medium devboxes Docker on every run No overage: upgrade when you hit the cap Starter $30 /mo 400 credits a month A steady lane of agent work. Start with Starter 2 warm slots — instant starts All sizes, up to 4 perf vCPUs / 16 GB Docker on every run Credit packs at $0.10 per credit Pro Most popular $75 /mo 2,000 credits a month The everyday fleet for one engineer. Start with Pro 3 warm slots — instant starts All sizes, up to 4 perf vCPUs / 16 GB Docker on every run Credit packs at $0.10 per credit Max $120 /mo 4,000 credits a month For a fleet that never sits idle. Start with Max 5 warm slots — instant starts All sizes, up to 4 perf vCPUs / 16 GB Docker on every run Credit packs at $0.10 per credit 1 credit = 6 minutes on a Medium devbox. Small = 0.5×, Large = 2×, XL = 4×. Idle and suspended devboxes bill nothing. Credit packs: 100 for $10, 250 for $25, 500 for $50, 1,000 for $100. Packs expire 12 months after purchase. Cancel anytime via the billing portal. FAQ Where do my API keys live? Encrypted at rest with AES-256-GCM under a key derived per user, and injected into your isolated VM only for the duration of a session. They're never written to logs, and you can revoke them at any time. Is my code safe? Each task runs in its own Firecracker microVM on a machine that is used once and destroyed afterward; nothing is shared or recycled between sessions. The devbox is open the whole time, so you can watch every command your agent runs. Do you train on my code? No. And because you bring your own keys, what your model provider does with your code is governed by your account and its settings; we're not in that loop. How do credits work? Credits meter active runtime only, per second. One credit is six minutes on a Medium devbox; Small runs at 0.5×, Large at 2×, and XL at 4×. Idle and suspended devboxes bill nothing, and warm slots are a plan entitlement that never consumes credits. Which agents and models can I use? Claude Code, Codex, and OpenCode, each running on your own subscription or key. Through OpenCode you can reach 40+ models across Anthropic, OpenAI, Google, DeepSeek, and more, and you can set the model and reasoning effort per task. Is there an API? Yes. A documented REST API with platform keys covers projects, tasks, automations, and usage, and a WebSocket API streams the live workspace: terminal, files, agent events, ports, and git. The CLI is built on the same surface. Can I cancel? Yes: self-serve via the billing portal, effective at the end of your billing cycle. The Free plan is permanent, so you can also just step down to it. Something else on your mind? Email us. Connect a repo. Bring your agent. Go. First PR in minutes. 1 Connect GitHub 2 Sign in with your Claude Code, Codex, or OpenCode account 3 Assign a task from Slack, Linear, or the app Stop firing agents into the void. Run your first agent in a devbox you can actually see. Free. Start building free Bring your own subscription. Your agent, your keys. Autonomous coding agents in a devbox you can watch, steer, and verify. Product The loop Pricing Docs Company About Contact X/Twitter GitHub Legal Privacy Terms Cookies © 2026 Aether Runtime, Inc. Not a black box. A devbox.