Orrery for agencies and freelancers

The AI coding agent
you can bill clients for.

A hard budget per client and a receipt for every task: tests passed, preview screenshots, cost. Plus a monthly AI-use log for client contracts that require AI disclosure.

Send me one real ticket from a client project. I'll help you run it in Orrery and you keep the receipt.

The problem

Fixed-price work and metered AI don't mix.

Metered tools blow up fixed bids

You quote a client a fixed price, then one long agent session eats the margin. Usage-billed AI tools give you a bill at the end of the month, not a limit at the start of the job, and nothing ties the spend to the client it was for.

Clients now ask how you use AI

More client contracts carry AI-use clauses: say when AI touched the code, which models, and where the code went. Answering from memory at the end of a project is slow, and it is hard to stand behind.

How Orrery handles it

Budget per client. Proof per task.

Orrery already proposes every change as a diff you approve, runs your tests, and writes a receipt for each run. The agency layer sorts that by client.

Available now

Per-client cost caps

Set a hard spend limit for each client. The agent stops at the cap instead of running over, so a fixed bid stays fixed.

Available now

Client receipts

Export a receipt for any task: what changed, which tests passed, preview screenshots, the model used and what it cost. Attach it to an invoice or a pull request.

Available now

Monthly AI-use log

One log per client per month: tasks, models, and where each one ran. A starting point for the AI-disclosure section of a client report.

Available now

Your keys or local models

Use your own provider keys, or run models on your own hardware (Ollama, LM Studio, vLLM), so client code can stay on your machines when the contract asks for it.

Available now

Hosted models included

Plans include hosted-model credits, so you can start without setting up a provider account. Credits stop hard at the limit and never overage.

Available now

Diffs you approve

The agent never writes straight to your repo. Every change is a reviewable diff, with rewind if a step goes wrong, so you can stand behind what you ship.

All of this is in Orrery today, from version 4.0.0-rc.51. Set a client up in Settings → Workspaces → Client.

Sample receipt

What a client receipt looks like.

An illustration of the planned export format. The client, ticket and numbers below are made up.

Example
Client
Example Bakery Co.
Task
#142 Add online pre-order form
Status
Approved and applied
Files changed
4 (+186 / −12)
Tests
38 passed · 0 failed
Preview
2 screenshots (desktop, mobile)
Model
Hosted model via Orrery
Ran on
Your machine (agent) · hosted model (inference)
Task cost
$0.84
Client budget
$12.40 of $50.00 used this month
Illustrative example only · not real client data
Pricing

Included in Orrery. No separate agency plan.

Free
$0your own hardware
  • The full agent on models you run yourself (Ollama, LM Studio, vLLM)
  • Per-client budgets, receipts and AI-use log
  • Client code never has to leave your machines
Pro, Max, Ultra
$40per month and up
  • Hosted models included: 20M / 50M / 100M credits a month
  • Your own provider keys (OpenRouter, OpenAI, Anthropic and more)
  • Everything in Free

Same plans as the rest of Orrery: see the Orrery pricing page. Credits are a hard stop, never an overage bill. Want to try it on real client work first? Send one ticket and we'll run it free →

Try it on one real ticket.

Pick a small ticket from a client project. I'll help you run it in Orrery, free, and you keep the receipt to judge it by.