Agent runs,
under control.
Orrery is an agentic code editor centered on Nexus: open a workspace, pick a model route, send a task, watch the run stream, then review usage, proof, and safety receipts before you accept anything.
Arbiter, DeepSeek API, and Doubleword credits — choose hosted routes per workspace and task.
Beta software. Agent output can be wrong or unsafe; keep backups and review changes before running or shipping them.
One console for workspaces, agents, routes, and receipts.
Nexus is the daily control surface: recent workspaces on the left, the active run in the center, and files, model route, agent details, proof, and usage on the right. It is built to make the common path obvious without hiding the review trail.
Illustrative lifecycle only. The sequence explains the product contract without presenting a fabricated interface or a simulated successful run.
Send work from one place, then decide what to trust.
The default flow is deliberately small: open a workspace, choose a route, send a prompt, watch the visible progress stream, then inspect summary, changed-file metadata, usage, and safety receipts. Deeper controls live in Nexus Settings.
Open folder
Start from the project folder you want Orrery to work in. Empty folders can be initialized as new workspaces.
Pick a route
Use subscription-hosted DeepSeek API, Doubleword, or Arbiter routes. Arbiter appears as a beta hosted coding route for eligible subscribers.
Run an agent
Nexus prepares workspace metadata, runs a safety check, and starts a registered agent when the route is ready.
Review receipts
Use proof, boundary, usage, and final summaries to decide whether to keep, revise, or discard the result.
Automation with a review boundary.
Orrery can make mistakes, and generated code may be insecure, incomplete, or unsuitable for your project. The product is designed to keep work reviewable: scope checks, permission gates, model-route labels, proof summaries, and usage receipts stay visible where supported.
Preview the setup.
Subscribe for hosted runs.
Preview setup before subscribing, then run agents through Orrery Cloud. Pro, Max, and Ultra add hosted DeepSeek API, Doubleword, and Arbiter credits plus managed connector automation.
This document describes the product contract. It is not a fabricated terminal session or a claim that a sample run succeeded.
Everything it does stays in view.
Orrery shows plans, tool activity, test output, review receipts, and usage data in one place. The log helps you audit the work, but it is not a substitute for your own review and backups.
Safety check first
Launches can record workspace scope, route state, permissions, and basic setup risk before work starts.
Searches your codebase
Ask about the project and Orrery can search code by meaning, not just keywords, with @codebase.
Scoped memory
Workspace memory is explicit and editable, so past decisions can be reused without turning every chat into hidden context.
Connected agents
Register local agents and connector-backed agents, then keep daily controls in Nexus and deeper setup in Settings.
Tool-aware runs
Use MCP and local tools where configured, while keeping raw source and keys out of cloud metadata by default.
Measure it over time
Track proof quality, usage, failures, and route behavior as tasks and models change.
Works with other editors
Plugs into other editors and agents through open, standard protocols.
Set the pace
Use model-aware effort and cost presets to keep routine work lean and deeper work deliberate.
See usage
Runs can show model route, usage, and credit receipts so hosted allotments are easier to track.
Cost-aware routing
Budget presets and route labels help you choose the right hosted-credit path for the job.
Nexus rooms
Group workspaces, agents, routes, runbooks, and approvals into reusable operating contexts.
What a supervised run must show.
Orrery keeps the operating contract concrete: each stage has visible evidence, a bounded action, and a decision that remains with you.
| Run stage | Visible evidence | System action | Your decision |
|---|---|---|---|
| Scope | Workspace and permission boundary | Prepare the run | Approve or revise |
| Route | Provider label and credit pool | Select hosted capacity | Confirm cost posture |
| Work | Progress, tools, and changed-file activity | Attempt the task | Observe or interrupt |
| Verification | Tests, diagnostics, and proof summary | Check the result | Inspect the evidence |
| Receipt | Usage and boundary record | Close the run | Keep, revise, or discard |
The interface may evolve during beta; these review boundaries are the stable product intent.
Clear about what crosses the network.
Hosted routes send the prompt and code context needed for a completion through Orrery Cloud to the configured provider. Ephemerent meters usage, does not retain relay content beyond fulfilling the request, and does not use your code or prompts to train its own models.
Explicit hosted route
Nexus labels the selected DeepSeek API, Doubleword, or Arbiter route before a run starts.
Purpose-limited relay
Only the prompt and context needed for the completion are relayed to the configured provider.
Content is not metering
Stored usage counters are token totals and timestamps, not copies of prompt content.
Your review remains final
Keep source-control backups and inspect changes before accepting, running, or shipping output.
Subscribe to run Orrery.
Orrery is a paid product. Preview Nexus, open a workspace, and configure routes before subscribing; Pro, Max, and Ultra unlock agent runs, large hosted credit pools, cloud features, managed connectors, proof vaults, and usage receipts subject to beta availability and provider limits. Hosted routes use prompt caching and token-efficient run context so included credits — and estimated API usage value — stay large.
Paid individual agent work with hosted credits and Nexus operations.
- DeepSeek API - 200M credits/mo
- Doubleword - 200M credits/mo
- Arbiter - 100M credits/mo
- Est. ~$2,400 API usage value/mo
- Nexus, Discord/mobile oversight, proof receipts
Bigger hosted-credit pools for daily multi-agent work.
- DeepSeek API - 600M credits/mo
- Doubleword - 650M credits/mo
- Arbiter - 400M credits/mo
- Est. ~$7,500 API usage value/mo
- More cloud/background run capacity
The largest hosted-credit pools and cloud automation capacity.
- DeepSeek API - 1.5B credits/mo
- Doubleword - 1.5B credits/mo
- Arbiter - 1.2B credits/mo
- Est. ~$18,000 API usage value/mo
- Research runs and proof vault capacity
Estimated API usage value assumes list-rate tokens with full prompt-caching and token-efficient context reduction. Public meters show credits/tokens and that estimate — not provider cost.
Governed agent work for engineering teams.
Shared workspaces, pooled credits, Slack requests, approval gates, audit receipts, and centralized policy. Business includes 5B pooled credits (~$25,000 est. API value); Enterprise includes 15B (~$75,000 est. API value). Organization entitlements sit alongside each member's personal plan.
Paid tiers are monthly subscriptions billed in advance via Stripe and renew automatically until canceled. Credits reset each billing month and do not roll over. Hosted model prompts are proxied through Orrery Cloud to provider APIs. Beta features, routes, quotas, and providers may change or be unavailable. Agent output is not guaranteed. Legacy local access is honored for existing buyers, but it is no longer sold and does not include hosted credits or cloud features. See Terms and Privacy.
Before you download.
What leaves my machine?
Which platforms are supported?
Can I use Orrery without subscribing?
Which hosted routes are included?
How is the winning attempt chosen?
Can I cancel anytime?
Open a workspace.
Send one task.
Get Orrery, choose a route, and keep the run reviewable from the first prompt.