tracklyng 0.1.1

Tracklyng — LLM cost tracking & observability. Capture LLM requests via OpenTelemetry GenAI instrumentation with a one-line install and zero call-site changes.

Tracklyng

Capture what can be logged from a real LLM request, with a one-line install in the client's app and zero changes to their call site.

pip install tracklyng

How it works

client app                       tracklyng lib                      Tracklyng
-----------                      --------------                     ----------
tracklyng.init(api_key=...) ──▶  sets up OpenTelemetry tracer
                                 turns on the GenAI instrumentation
                                   (every provider SDK)
client.models.generate_content(...)
        │  (real request still goes straight to the provider)
        ▼
   OpenTelemetry instrumentation captures a span
        │
        ▼
   our SpanExporter  ──────────────────────────────────▶  hosted ingestion endpoint
   (+ token counts and host/location, lifted from the span & resource)

We do not maintain the monkey-patches ourselves — the opentelemetry-instrumentation-* packages do. tracklyng.init() just stands up the tracer, points the exporter at Tracklyng's managed ingestion endpoint, and flips the instrumentation on. They emit the standard gen_ai.* OpenTelemetry semantic conventions, so one span shape covers every provider. The exporter POSTs each captured span as JSON to the hosted endpoint, where it is stored in telemetry_spans.

Run it

Call tracklyng.init() once, before the first LLM request — the rest is the provider SDK code you already have:

import os

import tracklyng

tracklyng.init(api_key="tlk_live_...")  # the entire integration

# ...your existing, unmodified provider call:
from google import genai

client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])
client.models.generate_content(
    model="gemini-3.1-flash-lite",
    contents="In one sentence, what is observability for LLM apps?",
)

pip install tracklyng
export GEMINI_API_KEY=your-real-key
python your_app.py   # the captured span is sent to Tracklyng

The same tracklyng.init() covers every supported provider: an Azure OpenAI, Anthropic, Bedrock, or Vertex AI call produces a span with the same gen_ai.* keys.

Following Sentry's model for the credential: called with no api_key, Tracklyng runs as a no-op (nothing is captured or sent) so it is safe to leave in place across environments; a malformed key raises TracklyngConfigError at init(); a well-formed key that turns out to be revoked is reported and the batch dropped at export time, never crashing or blocking the host application.

Providers

tracklyng.init() switches on one OpenTelemetry instrumentation per LLM SDK we ship. A client only produces spans for the SDKs they actually use; others are skipped silently. Adding a provider = adding its instrumentor to _enable_instrumentors.

Provider	Instrumentation	Notes
OpenAI / Azure OpenAI	opentelemetry-instrumentation-openai	one instrumentor covers both — AzureOpenAI is part of the openai SDK
Anthropic / Claude	opentelemetry-instrumentation-anthropic	also covers Claude via the anthropic SDK's Bedrock client
AWS Bedrock	opentelemetry-instrumentation-bedrock	patches the boto3 bedrock-runtime client
Vertex AI	opentelemetry-instrumentation-vertexai	patches google-cloud-aiplatform
Google Gemini	opentelemetry-instrumentation-google-generativeai	patches the unified google-genai SDK

All five emit the same gen_ai.* attributes, so the captured span shape is identical across providers — our exporter reads one set of keys regardless of which provider made the call.

Data captured

Prompt and response content is captured verbatim. Each span carries the full gen_ai.* payload the instrumentation emits — including user messages, system instructions, and model completions (both the current semantic-convention attributes and event bodies). Nothing is redacted or stripped; the complete record is stored server-side in telemetry_spans.payload.

Because the library runs inside your application, anything your app sends to or receives from an LLM — including PII, PHI, or other regulated data — is part of the captured span. If you operate under GDPR/HIPAA or similar obligations, account for this prompt/response content in your data-processing assessment before enabling Tracklyng. (Earlier builds stripped content to metadata only; that behavior was removed — content is now persisted in full.)

Layout

Path	What
tracklyng/__init__.py	exposes tracklyng.init()
tracklyng/_capture.py	OTel setup, instrumentor list, and the span exporter that POSTs each span to the ingestion endpoint
tests/	unit tests for the span-to-record transform, the exporter, and init's failure modes