Observability for AI agents
Know what your AI agents cost. Catch failures before your users do.
Trakr instruments any AI agent workflow in 2 lines of code. Real-time cost per run, instant failure alerts, loop detection.
Built for teams shipping AI agents to production
import Trakr from '@trakr/monitor';
Trakr.init({ apiKey: process.env.TRAKR_API_KEY });Dashboard
See cost, failures, and loops the moment they happen
A real-time overview of every workflow — metric cards, run history, and alerts in one place.
Everything you need to run agents in production
Real-time cost monitoring
See cost per run, per workflow, and per model — updated in real time.
Learn moreRun comparison
Compare cost and performance between workflow versions. Available on Pro and Scale plans.
Learn moreRunning in production in under 5 minutes
Install the SDK, send your first run, and set up alerts — no framework lock-in.
Install SDK
npm install @trakr/monitorSend first run
import Trakr from '@trakr/monitor';
Trakr.init();
const run = Trakr.startRun('invoice-extractor');
// ... your agent code ...
await run.end({ status: 'success' });Set up alerts
// In the Trakr dashboard:
// Alerts → Create rule → Cost threshold
// Get notified via Slack, email, or PagerDutySimple, usage-based pricing
Start free. Upgrade when your agents scale.
Starter
For individual developers validating agents in production.
- 25K runs/mo
- 14 days retention
- 1 user
Pro
For teams shipping agents to production with real traffic.
- 100K runs/mo
- 90 days retention
- 3 users
Scale
For companies running multiple agent pipelines at volume.
- 1M runs/mo
- 1 year retention
- Unlimited
Start monitoring your agents today
Free tier includes 25K runs per month. No credit card required.
Get started free