Orientim
Setup Guide Contact Us

Spend control for autonomous agents · 01 / 09

You set the cap. Your agent can't cross it.

A local desktop app that hard-stops your AI coding agents at a dollar limit — not a warning after the money's gone. Caps per agent and across the account, budgets that reset themselves, and pricing exact enough to trust the number it stops on.

Free to start 100% local No telemetry
agent · claude-code-dev● metering
$0.00 / $50.00 cap
↔ scroll right — watch spend climb toward the cap

Why Orientim exists · 02 / 09

One stuck loop, and $100 is gone by morning.

You leave a coding agent running while you sleep. It hits a loop. The provider's dashboard warns you — hours later, once the money's already gone. Nothing, anywhere, actually stops it.

— a scene familiar to anyone who runs agents unattended. Orientim is the missing brake.

overnight · unattendedno limit
$0.00
11pm3am7am
nothing stopped it.

What you connect · 03 / 09

Works with the stack you already run.

One local link between your tools and every provider you run.

OpenAI Anthropic Gemini Groq OpenRouter
Works with Claude Code, Continue, Cline, Aider — and with your own code: LangChain, LlamaIndex, AutoGen, CrewAI, or anything speaking OpenAI chat completions or the Anthropic messages API. If you can set a base URL and the request leaves your machine, it counts.
Point it at any OpenAI-compatible endpoint and it meters that too — DeepSeek, xAI, Mistral, Together, a local vLLM. Including providers that don’t exist yet.
Chat, streaming and embeddings all bill against the same cap — so a RAG index or an agent's memory can't quietly spend around it.

Your key, protected · 04 / 09

Every agent runs. None of them holds your key.

Built for local, private use — we never see your key, and neither do your tools. It leaves your machine only for the provider it already belongs to.

# point your tool at Orientim, use the local key:
BASE_URL = http://127.0.0.1:8000/proxy/<agent>
API_KEY  = orientim-secure-key
tool sends orientim-secure-key Orientim swaps in sk-…real official API

An API key is unlimited authority — whoever holds it can spend without a ceiling. Orientim keeps that authority and hands your agents a key with a budget attached. You haven't added a meter to watch; you've issued a credential they can't overspend.

How it works · 05 / 09

Watch how it works.

A quick tour of the dashboard — everything you'll actually use, in the order you'll use it.

  • Add an agent and paste its provider key
  • Set a hard dollar limit
  • Track spend and exact cost, per provider
  • See an agent hit its cap and turn red
  • Read each request — model, tokens, exact cost

The panel · 06 / 09

One panel. Every agent, every provider, live.

Independent limits per key. When one hits its ceiling it turns red and stops — everything else keeps running.

🟠 Claude Code Devanthropic
$20.00 / $20.00
● Limit reached
🟢 Production GPT-4oopenai
$45.20 / $50.00
● Active · 90%
🔵 Gemini Experimentsgemini
$1.24 / $10.00
● Active · 12%
🔶 OpenRouter Poolopenrouter
$12.80 / $30.00
● exact cost from provider

Every call is metered from each provider's own rates. If a provider changes its pricing, you edit it yourself in the dashboard — changes apply to the very next call.

What’s inside · 07 / 09

One licence. The whole instrument.

Not a meter with a limit bolted on — four things that have to be right before a hard stop means anything.

Controlthe stop
  • A hard cap per agent. Cross it and the next request is refused, not logged.
  • An account ceiling above them all — when the total lands, every agent stops.
  • Budgets that reset themselves: daily, weekly, monthly, or one-off forever.
  • A heads-up at 80%, once per crossing, not on every call after it.
  • Stop all agents in one press, and pause or resume any one of them.
  • Caps are independent — one agent hitting its ceiling leaves the rest running.
Accuracythe number
  • Anthropic prompt caching is priced properly — cache reads at 0.10×, writes at 1.25×. Claude Code caches hard, and treating those as ordinary tokens is how a cached agent looks ten times more expensive than it is. Other providers report cache hits differently; their cached tokens bill at the full input rate for now.
  • Embeddings billed at embedding rates for OpenAI, Gemini and Voyage models, not at a chat rate that would overcharge them enormously and trip your cap on the first index. An embedding model we don’t list is still priced as one, and flagged so you can correct it.
  • OpenRouter is exact — it reports real cost, so we use its figure rather than an estimate.
  • Every rate is yours to edit, and a model too new to be listed can be priced by hand.
Daily useliving with it
  • A desktop alert the moment an agent is stopped — you find out from your machine, not from the invoice.
  • Test connection sends one real token through the whole path, so a mistyped key fails while you’re still looking at it.
  • Pick your client and it writes the setup line for you — the id is never retyped.
  • Logs keep the input/output split, the stop reason and which price was used, so a surprising number can be traced.
  • Offers to start with Windows during install, so being protected is the default rather than something to remember.
  • Installs without admin rights, and your agents, keys and history survive an uninstall.
Trustwhat stays yours
  • Runs entirely on your machine. No account, no cloud, no telemetry.
  • Your provider key is masked everywhere and injected onto one request only — the one going to the provider it already belongs to.
  • Your tools never hold the key. They hold a local one that works nowhere else.
  • One licence check, the first time. After that it never contacts us again.

Windows 10 / 11 Free until it has metered $20 of your own spend then $39.99 once · no subscription

Straight answers · 08 / 09

The questions worth asking before you install it.

QIs my API key safe?
It stays in a file on your own machine and is added only on the outbound HTTPS call to the provider it already belongs to. We never receive it, and your tools never hold it — they talk to Orientim with a local key instead.
QWindows warns me when I run it. Why?
Because the installer isn’t code-signed yet — a certificate costs a few hundred a year and I’d rather earn it from sales than charge for it first. Windows shows a blue screen with no obvious way past: click More info, then Run anyway. If you want to check the file is the one I published, its SHA-256 is b97d5b45bc1ec3b1dd0230e34be4025c2039c1c00ef537a81ee4a882d2b48771.
QWill I know when an agent is stopped?
Twice. A desktop alert at 80% of the cap, while there's still room to act — and another the moment the agent is stopped. Each fires once, not on every request. Raise the cap and it resumes.
QDoes it phone home?
One license check when you activate, then never again — no account, no telemetry. After that the only traffic it makes is forwarding your requests to the AI provider. Verify with Wireshark.
QDoes it work with Cursor?
No. Cursor routes requests through its own servers, so a local proxy never sees the traffic. It works with Claude Code, Continue, Cline, Aider, and anything that calls the API directly from your machine.
QWhat are its limits?
It stops the next request, not mid-request — a provider only reports cost after it answers, so the call that crosses your cap finishes, and so does anything running beside it. The overshoot is exactly that: whatever was already in flight. One agent working normally has one request in the air, so you land within pennies of your number. Fire twenty calls at once and you carry twenty. It's a safety net, not DRM.
QCan I try it before paying?
Yes — the whole product, until it has metered $20 of your own API spend. That's traffic you were sending anyway, not money you give us. No card, no account, no clock: the meter only moves when Orientim is working, so it can't expire while you're busy. When it's reached, requests stop — Orientim never keeps forwarding with the caps switched off.
QWhat if it's not for me?
14-day money-back, no questions asked.

The hard stop · 09 / 09

Draw the line before your agent finds the edge.

Install it in a minute, decide later. The bill it exists to stop is usually three figures.

Free to start / then $39.99 once

✓ Free until it has metered $20 of your own spend · one-time, no subscription · 14-day money-back

agent · claude-code-dev● at the cap
$50.00 / $50.00
HTTP 402 — BLOCKED. No further spend until you raise the limit.
$0.00 / $50.00
SPEND
← → keys · scroll · swipe