token-dashboard v0.1.0

token-dashboard v0.1.0 released.

Run via Docker

docker pull ghcr.io/unityinflow/token-dashboard:0.1.0
docker run -p 8080:8080 -p 4317:4317 \
  ghcr.io/unityinflow/token-dashboard:0.1.0

Then open http://localhost:8080

Run via fat jar (requires Java 21+)

Download the attached token-dashboard-0.1.0-all.jar and:

java -jar token-dashboard-0.1.0-all.jar

See the auto-generated notes below for changes since the previous release.

Full Changelog: v0.0.1...v0.1.0

v0.0.1

Initial release of token-dashboard — real-time AI agent token cost dashboard.

What's included

• Real-time burn rate display (tokens/minute, projected cost)
• Per-agent and per-model cost breakdowns
• Session history with cost trends
• Anomaly detection (flags 2x+ normal cost agents)
• Budget alert webhooks (Slack + custom URL)
• SQLite backend (zero cloud dependency)
• HTMX frontend (zero JavaScript build step)
• OTLP gRPC receiver (ingests budget-breaker metrics)
• REST API for integration
• Docker support

Run it

docker run -p 8080:8080 unityinflow/token-dashboard

Or build from source:

./gradlew run

Tests

99 tests across 16 test files.