RUNTIME · FREE IN OCTOBER · BETA

Installs locally. Approves on the web. Free in October.

The CLI runs on your machine, sees traffic from all your agents, and builds a single queue with pre-calculated risk. The same queue appears in the browser when you link the machine. Without changing Claude, Cursor, Codex, or OpenCode.

Request early access →Orchestra: the next step

CLI for macOS, Linux, and Windows · Web approval · Free in October

Approval queue · your-machine4 pending
claude-codeWrite apply_coupon.rbinside the expected surface of AURA-118low risk
opencodeRun rails db:migratecreates coupons table · reversiblemedium risk
antigravityRead 14 files from checkout/read onlylow risk
codexDelete legacy/payments.rbtouches critical path · 312 lineshigh risk
4 agents · 3 providers · terminal or webinstant
Precisely

Three facts. Nothing more.

1 · It installs locally

The CLI watches your agents' traffic on your machine. macOS, Linux, and Windows. Automatic detection of known agents. You stay in the same terminal as always.

2 · You see and approve on the web

You link the machine with a pairing code. The queue appears in the browser. You approve or reject; the decision reaches the terminal. Without that link, nobody approves from outside.

3 · Free in October

Runtime —CLI and web approval— is free in October with early access. It does not call models to decide: risk comes from rules. Everyone who uses it makes the platform better. Many projects at once? Orchestra organizes them by mission and by role. Included in Pro from 2027.

What it does not do yet

Better a short list than a long promise.

  • —It does not write code. It is not an agent. It governs the ones you already use.
  • —It does not orchestrate by mission or role. That is Orchestra, in Pro from 2027.
  • —It does not test behavior. That is AURA QA, under construction, no date.
  • —It does not replace Review. The queue approves agent actions; the PR verdict lives on GitHub.
The problem

No vendor is going to build this for you.

Anthropic, OpenAI, Google, and Cursor each build their own orchestrator — for their agent, with their subscription. Nobody will govern competitors' agents. Meanwhile, you jump between terminals.

Missed approvals

A hidden tab, a stopped agent, a lost afternoon. With ten agents, the problem multiplies by ten.

Blind decisions

Which model plans better? Which writes more reliable tests? Today: perceptions. Nobody has data.

Vendor cages

Every tool wants to be the only one. Switching agents when credits run out means switching the entire flow.

CLI

Install the CLI and keep working as usual.

Runtime watches your agents' traffic locally. Nothing changes in your flow, except that everything now goes through one place.

  • macOS, Linux, and Windows
  • Automatic detection of known agents
  • Low / medium / high risk per action
aura runtimeBeta
# install (closed beta · the link arrives with your invite)$ aura runtime init✓ machine linked: cerebro (linux)✓ agents detected: claude-code, opencode, codex✓ approval queue active $ aura runtime watch[claude-code] write apply_coupon.rb  low risk[codex]       rm legacy/payments.rb  high risk ⚠→ a / r / d (approve / reject / detail)
Early access · October

Free in October. Get into the beta ahead of everyone else.

Tell us how you work and we send access in order of arrival. Teams using three or more distinct agents get priority. Orchestra —flows, missions, roles— arrives with Pro from 2027.

Request Runtime access

We write back within 72 hours.

No spam. We use your email only for the beta and to notify you when Runtime is public.

✓ Received. We will write within 72 hours with your access.

Install Runtime.
Approve on the web.

October beta. Free with early access. Orchestra —flows, missions, roles— is the next step, included in Pro from 2027.

Request early access →View Orchestra

“The one who decides does not compete in the game.”