Star 历史趋势
数据来源: GitHub API · 生成自 Stargazers.cn
README.md

AIUsage icon

AIUsage

One dashboard for all your AI subscriptions

Track quotas, costs, and accounts across 10+ AI providers.
Built-in proxies for Claude Code, Codex, OpenCode and Claude Science — any OpenAI-compatible model.

中文说明 · English

macOS 14+ SwiftUI Release License Stars Downloads

Sponsored by
Sucloud
500+ AI models · Text, image, video & audio · Top models included · Pay-as-you-go

AIUsage dashboard


Table of Contents

Features

FeatureDescription
12+ AI ProvidersCodex, Copilot, Cursor, Antigravity, Kiro, Warp, Gemini CLI, Droid, Claude Code, OpenCode, Kimi, MiniMax — one dashboard
Multi-accountMultiple accounts per provider, independent refresh, one-click CLI switching
Usage StatsUnified cost & token breakdown from Claude/Codex proxy archives, token-only non-proxy Codex sessions, and OpenCode's local session ledger — per-model trends, time-period analysis, source-aware aggregation
Claude Code ProxyUse Claude Code with DeepSeek, GPT, Ollama or any OpenAI-compatible model; Anthropic passthrough for usage logging
Codex ProxyPoint Codex CLI at any OpenAI-compatible upstream; unified switcher across subscription accounts and API nodes, surgical config.toml merge
OpenCode ProxySwitch OpenCode across upstreams via a managed opencode.json block — OpenAI-compatible, Anthropic and Responses protocols, per-node usage attribution, per-model pricing and optional request logging
Claude Science ProxyLaunch local Claude Science without a Claude subscription and route its inference to any third-party model; local virtual login and an isolated sandbox, with optional adoption so the double-clicked desktop app is login-free too — never touching your real credentials
Global ProxyOne fixed local endpoint per agent — hot-swap the active upstream node with zero CLI restart, per-node cost attribution, and automatic cross-track port arbitration
Unified API ProvidersConfigure one upstream (Base URL, format, key, model library/pricing) once and distribute it to Codex / Claude / OpenCode at once; linked nodes inherit from the master and sync on change, with per-field local overrides
Call AnalyticsCount MCP / Skill / tool calls across Claude Code, Codex & OpenCode from local session logs — Top-N rankings, daily trend, and per-app zero-call ("zombie" skill/MCP) detection; read-only, zero instrumentation
Menu BarMulti-account status bar icons, quota/cost metrics, per-proxy node switchers, quick-glance popover, colored progress bars
Credential VaultmacOS Keychain storage for all managed credentials

Preview

DashboardProvider monitoring
DashboardProvider & Multi-account Monitoring
Claude Code proxy node managementClaude Code proxy configuration
Claude Code Proxy · Node ManagementClaude Code Proxy · Configuration
Codex proxyOpenCode proxy
Codex Proxy · Nodes & SubscriptionsOpenCode Proxy · Nodes & Stats
Claude Science proxy
Claude Science Proxy · Login-free Local Science
Usage statsMenu bar
Usage Stats (Claude, Codex & OpenCode)Menu Bar
Call Analytics
Call Analytics · MCP / Skill / Tool Usage

Install

Download .dmg or .zip from the Releases page.

Universal Binary — runs natively on both Apple Silicon and Intel Macs (macOS 14+).

Proxies

AIUsage ships four independent proxies — for Claude Code, Codex (Codex CLI), OpenCode and Claude Science — each with node management, usage logging and a unified switcher.

Claude Code Proxy

Use Claude Code CLI with any OpenAI-compatible model, or transparently log Anthropic API usage.

ModeWhat it does
OpenAI ProxyTranslates Claude API → OpenAI format. Works with DeepSeek, GPT, Azure, Ollama, etc.
Anthropic PassthroughForwards requests as-is, logs input/output/cache tokens for cost tracking

Quick start: Open AIUsage → Claude Code Proxy → New Node → Configure → Activate. Settings are written to ~/.claude/settings.json automatically.

Codex Proxy

Point the Codex CLI at any OpenAI-compatible upstream (Responses API), and switch between subscription accounts and API nodes from one place — they are mutually exclusive, so only one identity is ever active.

CapabilityWhat it does
OpenAI-compatible upstreamRoutes Codex CLI through any responses-compatible endpoint
Unified switcherOne toggle across subscription accounts (~/.codex/auth.json) and API nodes (config.toml)
Surgical config mergeInjects managed blocks into ~/.codex/config.toml while preserving your own settings; global fragment + per-node TOML override
cc-switch syncOne-click import of Codex providers from local cc-switch (upstream / model / key), preserving model_reasoning_effort, mcp_servers and other settings; deterministic-id dedup avoids duplicate nodes (symmetric with Claude)

Quick start: Open AIUsage → Codex Proxy → New Node (or pick a subscription account) → Configure → Activate. ~/.codex/config.toml is merged automatically. Already on cc-switch? Hit "Sync cc-switch" in the toolbar to import in one click.

OpenCode Proxy

Switch OpenCode between any number of upstreams without hand-editing opencode.json. AIUsage injects a managed provider block (and points the top-level model at it), then restores your original config on deactivate — the backup is the source of truth, so takeover is idempotent.

CapabilityWhat it does
Multi-protocolOpenAI-compatible (@ai-sdk/openai-compatible), Anthropic (@ai-sdk/anthropic) and OpenAI Responses (@ai-sdk/openai) — the npm package follows the node's protocol
Direct or proxy modeDirect rewrites opencode.json to talk to the upstream; proxy mode points it at a local passthrough process for per-request logs (usage/cost still comes from opencode.db)
Per-node usageEach node writes a distinct managed providerID, so the local OpenCode session ledger attributes tokens and models.dev-priced cost back to the right node
Model library & pricingPer-node model list with independent per-model pricing (USD/CNY); pick the default model from the library and switch from the node card
cc-switch syncOne-click import of OpenCode providers from local cc-switch (upstream / models / key / pricing), deterministic-id dedup, configurable cc-switch directory

Quick start: Open AIUsage → OpenCode Proxy → New Node → Configure models & pricing → Activate. ~/.config/opencode/opencode.json is taken over automatically (requires OpenCode ≥ 1.2 for usage tracking).

Claude Science Proxy

Launch a local Claude Science instance without a Claude subscription, and route its inference to a third-party model of your choice through the local proxy — while keeping tool calls, Skills, MCP and code execution intact. For personal study and research only; use at your own risk.

CapabilityWhat it does
Local virtual loginForges a self-made virtual OAuth credential in an isolated data-dir to pass the login gate — zero Anthropic contact, never touching your real ~/.claude-science
Inference via third-partyPoints ANTHROPIC_BASE_URL at the reused local QuotaServer, strips inbound OAuth, injects your third-party key, and maps opus/sonnet/haiku tiers to the node's real models
Isolated sandboxSeparate HOME / port (14410) / data-dir / keychain, zero impact on the real instance; one click opens the logged-in page in your browser
Adopt the real instance (optional)An 8765 reverse proxy plus a decoupled internal daemon (14411) makes the double-clicked desktop app login-free too; only the runtime operon.lock is rewritten, real credentials are never touched
Shared node poolReuses the Claude-family nodes from the Claude Code proxy; hot-swap the upstream at runtime, transparent to Science

Quick start: Prepare an upstream node on the Claude Code proxy page first → Open AIUsage → Claude Science Proxy → pick a node → One-click start; your browser opens the logged-in Science automatically. See docs/CLAUDE_SCIENCE_INTEGRATION.md for the technical design.

Global Proxy

Instead of activating one node at a time, run a single fixed local endpoint per agent and hot-swap the active upstream behind it — the CLI never restarts and its config never changes.

CapabilityWhat it does
Fixed endpointEach agent points at one stable local port once; switching upstreams is in-process and CLI-transparent
LAN access (optional)Bind the global proxy to 0.0.0.0 so other devices on your LAN can reach it via your machine's IP (off by default)
Hot-swap active nodeChange the active node with zero restart; each request is rewritten to that node's real upstream model
Per-node attributionCost and usage are recorded against the real active node and model, not a generic global bucket; ports are arbitrated across all three tracks to avoid collisions

Unified API Providers

Configure an upstream once and reuse it everywhere. Under Providers → API Providers, define a provider (Base URL, API format, key, model library and pricing) and distribute it to any combination of the three proxies — each gets a linked node.

CapabilityWhat it does
Configure once, distributeOne config feeds Codex / Claude / OpenCode; a compatibility matrix limits where each format can go
Inherit + local overrideLinked nodes follow the master and sync on change; editing a shared field on one node turns it into a local override that no longer syncs
Safe lifecycleIdempotent re-distribution (no duplicates), port deconfliction for new nodes, and cascade delete or unlink when removing a master

Usage and billing details for Claude Code and Codex are documented in docs/USAGE_AND_BILLING.md. OpenCode cost is read directly from its local session ledger (opencode.db), pre-priced per models.dev.


Call Analytics

See which MCP servers, skills and tools you actually use. AIUsage parses the local session logs of Claude Code, Codex and OpenCode — read-only, with zero instrumentation — and turns tool calls into usage insights: spot the MCP servers you rely on, and clean up "zombie" skills that were installed but never called.

CapabilityWhat it does
Top-N rankingsMCP servers (folded by server), skills and built-in tools ranked by call count, with stable tie-breaking
Daily trendPer-day call volume over the selected 7 / 30 / 90-day or all-time window
Zero-call detectionFlags installed-but-never-called skills and configured-but-unused MCP servers — scoped per app, so each tool's own cleanup candidates are actionable
Per-source scopeFilter by Claude Code / Codex / OpenCode or view all; skills and MCP are attributed to each tool by its own skill directories and config files

Codex skill calls are heuristic — Codex has no discrete skill-invocation event, so they are inferred from SKILL.md reads. Rule-hit counts are not tracked: rules are injected as context, not discrete calls.


Acknowledgements

Inspired by CodexBar and Quotio.

Sponsor

Sucloud

Sucloud — AI API aggregation platform with 500+ models.
Full modality coverage (text, image, video, audio) including Claude, GPT, Gemini and more.
RMB payment supported, no overseas card required.

Models Pricing Bonus

Support the Author

If AIUsage helps you, consider buying the author a coffee. Your support helps keep the project maintained and improved.

Donation QR code

Friendly Links

License

Apache License 2.0

Star History

Stargazers over time

关于 About

One dashboard to manage all your AI subscriptions — track quotas, costs, accounts, Claude Code proxy, and Codex proxy in one place.

语言 Languages

Swift99.5%
Shell0.4%
Python0.1%

提交活跃度 Commit Activity

代码提交热力图
过去 52 周的开发活跃度
472
Total Commits
峰值: 146次/周
Less
More

核心贡献者 Contributors