Scattered billing
Juggling 4+ provider dashboards to understand what you're spending.
Local-first AI observability
See every AI token you spend.
One dashboard for OpenAI, Anthropic, Google, DeepSeek, xAI, Ollama, and more. Runs locally. Your data never leaves your machine.
Your AI Tools
Cursor
Claude
Codex
Any Tool
TokenPulse Proxy
โก Token counting
๐ฐ Cost tracking
๐พ Local SQLite logging
AI Providers
OpenAI
Anthropic
Google
xAI
DeepSeek
Kimi
Mistral
Ollama
Local Dashboard
๐ Spend & trends
๐ฏ Budgets & alerts
๐ Optimizer signals
The bottleneck
The problem with AI spending
The more models and providers you use, the harder it gets to understand where cost is coming from and what to change.
Invisible local usage
Running Ollama and LM Studio with zero visibility into what they're doing.
No single view
No way to compare cloud costs vs local performance in one place.
How it works
Three steps. Five minutes.
TokenPulse sits in the request path, records the useful parts, and gives you one local dashboard instead of eight tabs.
01
Point your tools at TokenPulse
Change one environment variable. That's it.
export OPENAI_BASE_URL=http://localhost:410002
TokenPulse intercepts and logs
Every request flows through the proxy. Usage metadata is stored locally in SQLite.
03
Open your dashboard
Real-time spend, model breakdowns, budgets, and optimization
signals at localhost:4200.
Dashboard
Your AI command center
Track live requests, budget pressure, model performance, and cost-saving opportunities from one dashboard built for daily use.
Optimization hints
Catch expensive model choices before they compound.
Usage heatmaps
See when teams, agents, or scripts actually spike.
Features
Built for power users
Everything important stays local, but the visibility is good enough for serious day-to-day optimization work.
10+ Providers
OpenAI, Anthropic, Google, xAI, DeepSeek, Kimi, Mistral, Groq, Ollama, LM Studio โ all through one proxy.
Real-time cost tracking
Per-request token counts and cost calculation as requests flow through.
Budget alerts
Set spending limits, get notified before you blow through them.
Local-first
SQLite on your machine by default. Optional cloud sync and team features coming soon.
Streaming support
Full SSE streaming passthrough with live token counting.
Cost optimizer
Detects model misuse and suggests cheaper alternatives that fit.
Forecasting
Monthly spend projections based on your actual usage patterns.
CSV export
Export everything for spreadsheets, reports, or your own analysis.
Comparison
How TokenPulse compares
Local model visibility and zero-account setup are the main differentiators, especially if you already run AI tools on your own machine.
| Feature | TokenPulse | Helicone | LiteLLM | CostGoat |
|---|---|---|---|---|
| Local model tracking | โ | โ | Partial | โ |
| Real-time proxy | โ | โ | โ | โ (polls) |
| 100% self-hosted | โ | โ (OSS) | โ (OSS) | โ |
| No account for core features | โ | โ | โ | โ |
| Data stays local | โ | โ | โ | โ |
| Price | Free core ยท Pro from $9.99/mo | Free-$500/mo | Free | $9/mo |
Getting started
Up and running in 5 minutes
Clone the repo, build the Tauri app, start the dashboard, and point your tools at the local proxy.
๏ฃฟ macOS
๐ง Linux
Read the full getting started guide
git clone https://github.com/TokenPulse26/TokenPulse.git
cd TokenPulse/src-tauri && cargo build --release && cd ..
python3 web-dashboard.py
# Open http://localhost:4200