https://github.com/janekbaraniewski/openusage
The one dashboard you’ve been looking for — track spend and usage across Claude, Cursor, OpenRouter, Copilot, Gemini, Codex, and more.
https://github.com/janekbaraniewski/openusage
ai-cost ai-cost-tracking ai-spending ai-usage claude claude-code claude-code-usage claude-usage-monitor codex coding-agents copilot copilot-usage cursor gemini-cli llm-usage openrouter openrouter-usage
Last synced: 8 days ago
JSON representation
The one dashboard you’ve been looking for — track spend and usage across Claude, Cursor, OpenRouter, Copilot, Gemini, Codex, and more.
- Host: GitHub
- URL: https://github.com/janekbaraniewski/openusage
- Owner: janekbaraniewski
- License: mit
- Created: 2026-02-10T01:31:54.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2026-03-05T14:37:07.000Z (2 months ago)
- Last Synced: 2026-03-05T14:53:16.788Z (2 months ago)
- Topics: ai-cost, ai-cost-tracking, ai-spending, ai-usage, claude, claude-code, claude-code-usage, claude-usage-monitor, codex, coding-agents, copilot, copilot-usage, cursor, gemini-cli, llm-usage, openrouter, openrouter-usage
- Language: Go
- Homepage:
- Size: 15.8 MB
- Stars: 11
- Watchers: 0
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Agents: AGENTS.md
Awesome Lists containing this project
README
OpenUsage.sh: terminal-first local quota and usage tracking for Claude Code, Codex CLI, Cursor, Copilot, and OpenRouter.
Install ·
Providers ·
Config ·
Keybindings ·
Development
---
OpenUsage is the terminal-first local dashboard published at [openusage.sh](https://openusage.sh/). Publicly, the clearest brand reference is **OpenUsage.sh**. It auto-detects AI coding tools and API keys on your workstation and shows live quota, usage, spend, resets, rate limits, and model data in your terminal. It is built for mixed-tool workflows across Claude Code, Codex CLI, Cursor, Copilot, Gemini CLI, OpenRouter, OpenAI, Anthropic, and more. Zero config required — just run `openusage`.
Run it side-by-side with your coding agent:
OpenUsage running alongside OpenCode monitoring live OpenRouter usage.
## Install
### macOS (Homebrew, recommended)
```bash
brew install janekbaraniewski/tap/openusage
```
### All platforms (quick install script)
```bash
curl -fsSL https://github.com/janekbaraniewski/openusage/releases/latest/download/install.sh | bash
```
### From source (Go 1.25+)
```bash
go install github.com/janekbaraniewski/openusage/cmd/openusage@latest
```
Requires CGO (`CGO_ENABLED=1`). Pre-built binaries are also available on the [Releases](https://github.com/janekbaraniewski/openusage/releases) page.
## Run
```bash
openusage
```
Auto-detection picks up local tools and common API key env vars. No config needed.
## Track coding agent usage across multiple platforms
Native dashboards show one provider at a time. OpenUsage gives you one local-first view across coding agents, API platforms, and local runtimes so you can answer:
- Which tool or provider is burning budget?
- Which model caused the spike?
- Which quota or reset is getting close?
- Which sessions, projects, or MCP tools drove the change?
It is built for end-user tool tracking, not for instrumenting a separate AI app with tracing SDKs or a billing backend.
If you want the full positioning argument, read the guide: [best way to track coding agent usage and quotas across providers](https://openusage.sh/best-way-track-coding-agent-usage-quotas-across-providers/).
If the question is whether this is the right fit versus a simpler local limits tracker, use:
- [OpenUsage.sh vs OpenUsage.ai](https://openusage.sh/docs/openusage-sh-vs-openusage-ai/)
- [Capability matrix](https://openusage.sh/docs/capability-matrix/)
- [Docs hub](https://openusage.sh/docs/)
## Features
- **Cross-provider tracking** — compare coding agents, API platforms, and local runtimes in one local dashboard
- **Zero config** — auto-detects your AI tools and API keys, just run it
- **Live dashboard** — see spend, quotas, rate limits, and per-model usage at a glance
- **17 providers** — covers coding agents (Claude Code, Cursor, Copilot, Codex, Gemini CLI), API platforms (OpenAI, Anthropic, OpenRouter, and more), and local tools (Ollama)
- **Background tracking** — collects data continuously, even when the dashboard is closed
- **Deep cost insights** — combine providers like OpenCode + OpenRouter for breakdowns by model, tool, and hosting provider
- **Tool integrations** — optional hooks for Claude Code, Codex CLI, and OpenCode provide richer, real-time usage data
- **Customizable** — 15+ built-in themes, adjustable time windows, configurable thresholds, provider reordering, plus external theme files
## Supported providers
17 provider integrations covering coding agents, API platforms, and local tools. See [docs/providers.md](docs/providers.md) for all providers with detailed descriptions and screenshots.
### Claude Code
**Detection:** `claude` binary + `~/.claude` directory
Tracks daily activity, per-model token usage, 5-hour billing block computation, burn rate, and cost estimation.
### OpenRouter
**Detection:** `OPENROUTER_API_KEY` environment variable
Tracks credits, activity, generation stats, and per-model breakdown across multiple API endpoints.
### All providers
#### Coding agents & IDEs
| Provider | Detection | What it tracks |
|---|---|---|
| **Claude Code** | `claude` binary + `~/.claude` | Daily activity, per-model tokens, billing blocks, burn rate |
| **Cursor** | `cursor` binary + local SQLite DBs | Plan spend & limits, per-model aggregation, Composer sessions |
| **GitHub Copilot** | `gh` CLI + Copilot extension | Chat & completions quota, org billing, session tracking |
| **Codex CLI** | `codex` binary + `~/.codex` | Session tokens, per-model breakdown, credits, rate limits |
| **Gemini CLI** | `gemini` binary + `~/.gemini` | OAuth status, conversation count, per-model tokens |
| **OpenCode** | `OPENCODE_API_KEY` / `ZEN_API_KEY` | Credits, activity, generation stats |
| **Ollama** | `OLLAMA_HOST` / binary | Local models, per-model usage |
#### API platforms
| Provider | Detection | What it tracks |
|---|---|---|
| **OpenAI** | `OPENAI_API_KEY` | Rate limits via header probing |
| **Anthropic** | `ANTHROPIC_API_KEY` | Rate limits via header probing |
| **OpenRouter** | `OPENROUTER_API_KEY` | Credits, activity, per-model breakdown |
| **Groq** | `GROQ_API_KEY` | Rate limits, daily usage windows |
| **Mistral AI** | `MISTRAL_API_KEY` | Subscription, usage endpoints |
| **DeepSeek** | `DEEPSEEK_API_KEY` | Rate limits, account balance |
| **Moonshot (Kimi)** | `MOONSHOT_API_KEY` | Balance breakdown (cash + voucher), org limits, tier; supports api.moonshot.ai (default) and api.moonshot.cn |
| **Perplexity** | Browser session at console.perplexity.ai | Tier, balance, lifetime spend, auto-reload, 30d usage analytics |
| **OpenCode (Zen + Console)** | `OPENCODE_API_KEY` / `ZEN_API_KEY` + browser session at opencode.ai | Zen models (API key) + balance, monthly limit/usage, subscription, payment method (cookie) |
| **xAI (Grok)** | `XAI_API_KEY` | Rate limits, API key info |
| **Z.AI Coding Plan** | `ZAI_API_KEY` / `ZHIPUAI_API_KEY` | Coding plan quotas, model/tool usage, daily trends |
| **Google Gemini API** | `GEMINI_API_KEY` / `GOOGLE_API_KEY` | Rate limits, model limits |
| **Alibaba Cloud** | `ALIBABA_CLOUD_API_KEY` | Quotas, credits, per-model tracking |
## Configuration
No config file needed — auto-detection handles everything. Override or extend via:
- macOS/Linux: `~/.config/openusage/settings.json`
- Windows: `%APPDATA%\openusage\settings.json`
```json
{
"auto_detect": true,
"ui": { "refresh_interval_seconds": 30 },
"accounts": [
{
"id": "openai-personal",
"provider": "openai",
"api_key_env": "OPENAI_API_KEY",
"probe_model": "gpt-4.1-mini"
}
]
}
```
Full reference: [`configs/example_settings.json`](configs/example_settings.json)
### External themes
You can define custom themes as JSON files loaded at startup from:
- `~/.config/openusage/themes/*.json` (macOS/Linux)
- `%APPDATA%\\openusage\\themes\\*.json` (Windows)
- Any extra directory in `OPENUSAGE_THEME_DIR` (path-list separated)
Theme files use the same color token fields as built-ins. Browse the bundled examples for reference shapes — every shipped theme lives at [`internal/tui/bundled_themes/`](internal/tui/bundled_themes/).
## Daemon
Background data collection, even when the dashboard isn't open:
```bash
openusage telemetry daemon # Run in foreground
openusage telemetry daemon install # Install as system service (launchd / systemd)
openusage telemetry daemon status # Check status
openusage telemetry daemon uninstall # Uninstall
```
Installed services snapshot the provider env vars currently set in your shell.
If you change API key env vars later, rerun `openusage telemetry daemon install`
to refresh the service environment.
Manage tool integrations:
```bash
openusage integrations list [--all] # List integration statuses
openusage integrations install # Install hook/plugin
openusage integrations uninstall # Remove
```
## Keybindings
| Key | Action |
|---|---|
| `Tab` | Switch views |
| `j` / `k`, `Up` / `Down` | Move cursor |
| `h` / `l`, `Left` / `Right` | Navigate panels |
| `Enter` / `Esc` | Open detail / back |
| `PgUp` / `PgDn` | Scroll tile |
| `[ ]` | Switch detail tabs |
| `r` | Refresh all |
| `/` | Filter providers |
| `t` | Cycle theme |
| `w` | Cycle time window |
| `,` | Open settings |
| `Shift+J` / `Shift+K` | Reorder providers |
| `?` | Help |
| `q` | Quit |
## Development
```bash
make build # Build binary to ./bin/openusage
make test # Run tests with -race and coverage
make lint # golangci-lint
make run # go run cmd/openusage/main.go
make demo # Preview with simulated data (no API keys needed)
```
Debug mode: `OPENUSAGE_DEBUG=1 openusage`
## License
[MIT](LICENSE)