Distributed traces
Follow a request from your API handler through retrieval, guardrails, the model call and back. Nested spans, exact token counts, full prompt and completion attached.
Kyvath traces every prompt, tool call and token so you can see latency, cost and quality per feature — and catch a regression on Tuesday instead of a customer complaint on Friday.
support.answer dropped 1.2% after prompt v14 · view diff
Follow a request from your API handler through retrieval, guardrails, the model call and back. Nested spans, exact token counts, full prompt and completion attached.
Slice spend by customer, feature, model or team. Set budgets and get pinged before the invoice, not after.
Score live traffic with LLM judges, heuristics or your own graders. Failures get sampled into a review queue automatically.
Compare v13 vs v14 by latency, cost and quality on the same traffic — then roll back in one click if the numbers disagree with the vibes.
Replay a full conversation with every tool result inline. Debug the weird one-in-ten-thousand case without asking the user for a screenshot.
Threshold, anomaly or eval-based. Route to Slack, PagerDuty or a webhook with the trace attached.
| Capability | Kyvath | Logs + dashboards | Generic APM |
|---|---|---|---|
| Nested LLM spans with prompts | ✓ native | manual | ✗ |
| Token-level cost attribution | ✓ per request | ✗ | ✗ |
| Online eval scoring | ✓ built in | ✗ | ✗ |
| Prompt version diffing | ✓ | ✗ | ✗ |
| OpenTelemetry compatible | ✓ | partial | ✓ |
| Self-hosted option | ✓ Enterprise | ✓ | ✓ |
| Setup time | ~4 minutes | weeks | days |
import { Kyvath } from '@kyvath/otel';
Kyvath.init({ apiKey: process.env.KYVATH_KEY });
// that's it — every LLM + tool call is traced
import kyvath, os
kyvath.init(api_key=os.environ['KYVATH_KEY'])
# auto-instruments openai, anthropic, langchain
“We found a $14k/month prompt leak in the first hour. Kyvath paid for itself before the trial ended.”

“The eval queue changed our release process. We no longer ship prompt changes on hope.”

$0
50k spans/month, 7-day retention, 1 project. Free forever for side projects.
Start freefrom $99
Volume-based, unlimited seats, 90-day retention, online evals, SSO.
Start trialcustom
Self-hosted, unlimited retention, custom graders, DPA, named engineer.
Talk to salesSpans are buffered and flushed asynchronously. Measured overhead is under 15ms p99 at 10k requests/minute, and the SDK can be configured to batch harder if you need more headroom.
OpenAI, Anthropic, Google, Mistral, Cohere, Bedrock, Azure OpenAI, Together, Groq, Fireworks and Ollama — plus LangChain, LlamaIndex and Vercel AI SDK.
Yes. A pre-flush hook lets you scrub prompts and outputs client-side. Enterprise plans also support full self-hosting with no outbound traffic.
Never. Traces are encrypted at rest with per-tenant keys and are deleted on your retention schedule.
Free for 50,000 spans a month. No sales call required.