Pricing

Pay for what the agent actually does

Free to start. Paid plans add more projects and concurrent agents, BYOK, bundled frontier allowance, Slack routing, and team workflow — with inference billed at provider cost, never marked up.

Kicking the tires

Try it on one repo, free.

Free

$0/ month

Curious indie hacker — kick the tires.

projects
5 projects
model
Kimi K2.6, included
caps
$100/mo of Kimi, then upgrade
  • Up to 5 projects — one per repo, in one cockpit
  • Kimi K2.6 included — free up to $100/mo
  • Bring your own keys on any paid plan (from $10/mo)
Start free →

Shipping every day

One repo, every day. Bring your own model keys, or let us handle inference.

BYOK

$10/ month

You already have API keys. Pay platform, not inference.

projects
5 projects
model
Kimi + your own keys
caps
$100/mo Kimi, then your keys
  • Everything in Free, plus your own keys
  • Bring Anthropic, OpenAI, Google, OpenRouter, or custom endpoints — switch per agent
  • Per-task cost in the app
Start with BYOK →

Solo

recommended
$20/ month

Active solo founder shipping every day.

projects
10 projects
model
Kimi + bundled frontier
caps
$100 Kimi + $20/mo frontier
  • $100/mo of Kimi, plus $20/mo of bundled frontier
  • Full task history + usage and billing
  • Email + GitHub mobile notifications
Choose Solo →

Running a portfolio

Every repo, in parallel — for operators and small teams.

Fleet

$79/ month

Portfolio operator running several products.

projects
25 projects
model
Bundled frontier + your keys
caps
$100 Kimi + $80/mo frontier
  • Up to 25 projects — one per repo, in one cockpit
  • $100/mo of Kimi, plus $80/mo of bundled frontier
  • Cross-project fleet view + cost roll-up
  • Slack notifications + per-repo channels
Choose Fleet →

Pro

$199/ month

Tiny team or small agency.

projects
Up to 100 projects
model
Bundled frontier + BYOK + priority
caps
$100 Kimi + $200/mo frontier
  • Up to 100 projects — one per repo, in one cockpit
  • $100/mo of Kimi, plus $200/mo of bundled frontier
  • Priority queue, no waiting in line
  • Auto-merge on green CI (opt-in)
Choose Pro →

Every plan includes

  • Isolated, encrypted sandbox per agent
  • Connect as many repos as you like
  • Plain-English tasks, a Pull Request back
  • GitHub-native — never pushed to your default branch
  • A per-task spend limit you control
  • Inference billed at provider cost, never marked up

What a task costs

Pay at cost. Spend stays predictable.

A typical small task costs cents to a few dollars of inference — you only pay for what the agent actually uses, at provider cost.

Set a per-task spend limit. If a task hits it we stop the task and refund the platform fee, so the cost of every task stays predictable. Retries on the same task are free.

Recurring workflows (/loop) and your own guardrail hooks are included on every plan — no separate add-on. A loop is just goals on a schedule: each iteration respects the same per-task cap, and you set a cap on the whole loop too, so an unattended fleet stays predictable.

$example: a "fix the flaky test" task ran 3 iterations and cost $0.40 of inference.

  • A human approves every PR — nothing merges without you.
  • Inference billed at provider cost — never marked up.
  • Never pushed to your default branch.

Billing

Billing questions

>What does BYOK actually mean?

Bring your own key. On any paid plan (from the $10/mo BYOK plan up), drop in an Anthropic, OpenAI, Google, OpenRouter, or custom OpenAI-compatible API key and the agent runs on it — we don't take a markup. The platform fee is what you pay us; inference cost is what you'd pay anyway. Free runs on the included Kimi K2.6 allowance.

>What counts as a task?

A task is one plain-English request that ends in a PR (or a failure log). Retries on the same task are free. A task that runs three iterations to land a PR still counts as one.

>Is anything unlimited?

No. Every plan is usage-based — you pay for the inference you actually consume, billed at provider cost. Every plan includes $100/mo of Kimi K2.6, free; paid plans add a bundled frontier allowance ($20/$80/$200 of Claude, GPT, and Gemini on Solo/Fleet/Pro). Past your allowance you upgrade for more headroom, or bring your own key.

>What happens when I hit my usage allowance?

We email you as you approach it. Agents pause at your monthly allowance until the next cycle or an upgrade — $100/mo of Kimi on Free and BYOK, plus the bundled frontier allowance on Solo/Fleet/Pro. On a paid plan, bring your own key to keep running on your own inference, billed by your provider.

>Cancellation?

Self-serve through the billing portal. Service continues to the end of the current billing period. Projects, agents, and task history archive for 30 days, then delete.

>Refunds?

7-day money-back guarantee on first month, no questions asked. After that, prorated to the next billing cycle.

>Annual billing?

Monthly only at launch. Annual (with two months free) ships once we have 90+ days of churn data to set the discount sensibly.


Get started

Start building today

Connect a GitHub repo, hand off a task in plain English, and get a reviewed Pull Request back. Start free and upgrade when your fleet needs more room.

Start free →

free to start · usage billed at cost · cancel anytime