v0.4.5 test release - 29 providers - desktop + mobile

See every AI provider’s limits, credits, and spend in one local-first dashboard.

LLM Status keeps rate limits, balances, spend, token totals, request totals, and local-model server state visible across 29 provider integrations on Windows, macOS, Android, and iOS.

View v0.4.5 test release GitHub downloads Review source

Test builds only. Read platform-specific install notes.

29providers 4platform tracks 0product telemetry
OAuth/session reuse Widgets Threshold alerts InfluxDB export Local servers Provider drift guards Safe backup imports No telemetry
Why it is different

Built for people who bounce between models all day.

29 providers from one engine

Quota, spend, reset windows, token totals, request totals, and local-model server state share one Rust provider core.

Native widgets and refresh

Android home-screen widgets and iOS WidgetKit previews keep critical providers visible between app opens.

Desktop command center

Tray and menu-bar status, full history dashboard, multi-account desktop slots, threshold alerts, and launch at login.

Several onboarding paths

Paste keys, reuse supported CLI sessions, sign in with OAuth/device flows, or opt into the desktop credential scanner.

Local servers included

Ollama and LM Studio are first-class status integrations with visible local-server URL fields on every client.

Local-first privacy model

Credentials stay in platform secure storage. There is no product telemetry. Optional metrics export goes only where you configure it.

Platform coverage

One provider engine, native surfaces everywhere.

Desktop gets the deepest control surface. Mobile gets native storage, refresh, alerts, and widget visibility where the platform allows it.

Windows

Tray flyout, dashboard, history, alerts, backup/import, credential scan, and optional metrics export.

macOS

Universal menu-bar app with Keychain storage, template icon, DMG, and app archive test packages.

Android

Native Compose test client with encrypted credentials, alerts, history sparklines, widget, and WorkManager refresh. Account-aware parity is now active source work.

iOS preview

SwiftUI Simulator preview with Keychain storage, multi-account management, history sparklines, local usage alerts, widgets, and secure OAuth refresh.

29 provider integrations, including local models

Reuse supported sessions and keys, connect with OAuth/device flows, paste API credentials, or monitor local Ollama and LM Studio servers.

  • Anthropic Claude
  • OpenAI Codex
  • GitHub Copilot
  • GitHub Actions
  • Google Gemini
  • Cursor
  • OpenRouter
  • DeepSeek
  • ElevenLabs
  • Deepgram
  • Groq
  • xAI Grok
  • z.ai
  • MiniMax
  • Fireworks AI
  • StepFun
  • Mistral
  • Cerebras
  • Rev.ai
  • LMNT
  • Aihubmix
  • Cloudflare Workers AI
  • Portkey
  • Requesty
  • LangDB
  • LiteLLM
  • Bifrost
  • Ollama
  • LM Studio
Privacy and trust

Your provider credentials stay under your control.

LLM Status uses secure operating-system storage, talks directly to the providers you configure, and does not collect product telemetry.

Secure local storage

DPAPI, Keychain, Android encrypted preferences, and iOS Keychain keep secrets off the marketing site.

Direct provider access

Credentials are used only to request usage information from the providers you connect.

Open implementation

Review the MIT-licensed source, architecture, provider fact sheets, and release gates on GitHub. View source.

Mobile parity: active source work

Bring the same provider twice—without losing the plot.

The next mobile pass makes an account instance, not a bare provider, the unit of monitoring. It is merged source work, not a v0.4.5 download claim.

Instance identity

One provider. More than one account.

Mobile monitoring is moving from a bare provider to a named account instance, so two Claude, Codex, or Copilot identities can stay distinct.

Native parity

The account follows the signal.

Android and iOS source now route secure credentials, OAuth refresh, history, alerts, and widget state through the account instance that owns them.

Non-secret import

Alert preferences, not credentials.

Android and iOS can import only alert enablement and thresholds from a user-selected desktop config. Provider keys, accounts, history, and provider settings stay untouched.

Track the implementation status in the open source work tracker. View mobile-parity progress.

Latest repository updates

The newest work hardens the app, not just the launch page.

Recent changes focus on truthful provider data, OAuth edge cases, import safety, and current platform foundations.

Provider drift guards

Checked-in response fixtures now fail closed when metric-bearing provider payloads lose required fields, preventing a misleading zero from looking healthy.

OAuth rotation discipline

Token responses are bounded, callback state is verified where supported, and rotated refresh tokens are persisted before a retry can race them.

Backup compatibility contract

Desktop imports validate schema versions, provider keys, slot names, sizes, thresholds, and metrics-export settings before changing local state.

Modern platform baseline

The shared UI now runs on React 19, while Android moves to AGP 9.3, compileSdk 37, Lifecycle 2.11, and the built-in Kotlin toolchain.

Current release

v0.4.5 is a serious test build, not a production distribution claim.

The latest repository work adds schema-drift guards, OAuth hardening, serialized refresh-token rotation, a backup compatibility contract, React 19, and a modern Android baseline. Distribution trust gates still remain before store-ready delivery.

  • Windows packages are unsigned and may trigger SmartScreen.
  • macOS packages are ad-hoc signed and not notarized.
  • Android APKs are test packages unless production signing is enabled.
  • iOS release artifacts are Simulator-only until Apple signing is configured.
Common questions

Before you install

Which platforms does LLM Status support?

Test builds are available for Windows 10/11, macOS 11+, Android 8+, and an iOS 16+ Simulator preview. Device and TestFlight distribution still require Apple signing.

Where are credentials stored?

Credentials use secure operating-system storage and are sent only to the provider APIs you configure. LLM Status does not collect product telemetry.

Is this a subscription?

No. Public test builds are available from GitHub. When paid early access is offered, it is a one-time $1.99 purchase through Stripe.

Are the current downloads production-ready?

No. Version 0.4.5 is a test release. Windows is unsigned, macOS is not notarized, Android uses a test signature unless production signing is enabled, and iOS is Simulator-only.

What changed in the latest repository updates?

Recent work adds provider schema-drift guards, stricter OAuth response and callback handling, serialized refresh-token rotation, safer backup imports, React 19, and a modern Android build baseline.

Can I use more than one account for a provider on mobile?

Desktop already supports multiple account instances. Android and iOS account-aware storage, management, refresh, history, alerts, and widgets are merged source work, but are not represented as a v0.4.5 release-download feature. Mobile transfer and backup remain separate delivery gates.

Current test release

v0.4.5 test build

29 providers, native desktop and mobile clients, widgets, alerts, local servers, and open source release notes.

View release notes and downloads