# Python SDK — auto-instrumentation

`pip install layerlens --extra-index-url https://sdk.layerlens.ai/package`. Sync and async. Source available at [`stratix-python`](https://github.com/layerlens/stratix-python).

## Client classes

The SDK exposes four public client classes, all backed by the same API:

* `Stratix` — primary sync client (authenticated, full surface)
* `AsyncStratix` — primary async client (authenticated, full surface)
* `PublicClient` — read-only client over the public catalog (no auth required)
* `AsyncPublicClient` — async variant of `PublicClient`

```python
from layerlens import Stratix, AsyncStratix, PublicClient, AsyncPublicClient
```

## Resources

<table data-view="cards"><thead><tr><th></th><th></th><th></th></tr></thead><tbody><tr><td><strong>Client configuration</strong></td><td>Stratix / AsyncStratix constructors, env vars, retries.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/client.md">Read</a></td></tr><tr><td><strong>Public client</strong></td><td>`client.public.*` and `PublicClient` for catalog access.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/public-client.md">Read</a></td></tr><tr><td><strong>Models and benchmarks</strong></td><td>`client.models`, `client.benchmarks` — get, get_by_key, add, create_custom, create_smart.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/models-benchmarks.md">Read</a></td></tr><tr><td><strong>Evaluations</strong></td><td>`client.evaluations` — create, wait_for_completion, get_many.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/evaluations.md">Read</a></td></tr><tr><td><strong>Scorers</strong></td><td>`client.scorers` — LLM-backed graders.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/scorers.md">Read</a></td></tr><tr><td><strong>Judges</strong></td><td>`client.judges` — create, get, get_many, update, delete.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/judges.md">Read</a></td></tr><tr><td><strong>Judge optimizations</strong></td><td>`client.judge_optimizations` — estimate, create, get, apply.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/judge-optimizations.md">Read</a></td></tr><tr><td><strong>Traces</strong></td><td>`client.traces` — upload, get, get_many, delete, get_sources.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/traces.md">Read</a></td></tr><tr><td><strong>Trace evaluations</strong></td><td>`client.trace_evaluations` — create, get, get_results, estimate_cost.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/trace-evaluations.md">Read</a></td></tr><tr><td><strong>Results</strong></td><td>`client.results` — get, get_all.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/results.md">Read</a></td></tr><tr><td><strong>Comparisons</strong></td><td>`client.public.comparisons` — compare, compare_models.</td><td>(see public-client)</td></tr><tr><td><strong>Errors</strong></td><td>Full exception hierarchy.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/errors.md">Read</a></td></tr></tbody></table>

## Auto-instrumentation

The `layerlens.instrument` subpackage provides drop-in instrumentation for LLM provider clients and supported frameworks. Importing `instrument_openai()`, `instrument_anthropic()`, or framework callbacks like `LangChainCallbackHandler` wraps the client so trace data is emitted automatically as your code runs.

See [Integrations](/6.-build-wire-your-code/sdk-python.md) for the production adapter list and [framework integration pages](/10.-integrate-connect-your-stack/10-integrate.md) for setup details.

## Authentication

```bash
export LAYERLENS_STRATIX_API_KEY="..."
```

```python
from layerlens import Stratix
client = Stratix() # picks up env var
client = Stratix(api_key="...") # or explicit
```

Environment variables:

| Variable                     | Default                           | Notes                                          |
| ---------------------------- | --------------------------------- | ---------------------------------------------- |
| `LAYERLENS_STRATIX_API_KEY`  | (required)                        | Primary API key env var                        |
| `LAYERLENS_STRATIX_BASE_URL` | `https://api.layerlens.ai/api/v1` | Override for self-hosted / staging deployments |

## Sync vs async

```python
# Sync
from layerlens import Stratix
client = Stratix()
result = client.evaluations.wait_for_completion(evaluation)

# Async
from layerlens import AsyncStratix
client = AsyncStratix()
result = await client.evaluations.wait_for_completion(evaluation)
```

Every resource is available in both sync (`Stratix`) and async (`AsyncStratix`) clients.

## Quick reference — every public method by resource

```
client.traces.upload(file_path).get(id).get_many().delete(id).get_sources()
client.judges.create(name=, evaluation_goal=, [model_id=]).get(id).get_many().update(id,...).delete(id)
client.evaluations.create(model=, benchmark=).get(id).get_many().wait_for_completion(evaluation)
client.trace_evaluations.create(trace_id=, judge_id=).get(id).get_results(id).estimate_cost(...).wait_for_completion(id)
client.judge_optimizations.estimate(...).create(...).get(id).apply(id)
client.results.get(evaluation=).get_all(...)
client.scorers.create(name=, description=, model_id=, prompt=).get(id).get_many().update(id,...).delete(id)
client.models.get([type=, name=]).get_by_key(key).add(...).create_custom(name=, key=, api_url=,...).remove(id)
client.benchmarks.get([type=, name=]).get_by_key(key).add(...).create_custom(...).create_smart(...).remove(id)
client.public.models.get(...)
client.public.benchmarks.get(...)
client.public.evaluations.get(...)
client.public.comparisons.compare(...).compare_models(...)
```

The exact signatures are in each per-resource page below.

## Adapters · CLI · Examples · Security · Troubleshooting

Deeper SDK material ported from the `stratix-python` repo:

<table data-view="cards"><thead><tr><th></th><th></th><th></th></tr></thead><tbody><tr><td><strong>Adapters</strong></td><td>Per-framework + per-provider instrumentation guides (LangChain, LlamaIndex, CrewAI, OpenAI, Anthropic, Bedrock,...). Also: OTLP sink, Pydantic v1/v2 matrix, certification suite, testing.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/adapters/frameworks-langchain.md">Browse</a></td></tr><tr><td><strong>CLI</strong></td><td>`stratix` CLI — getting started, full command reference, 15 workflow recipes.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/cli/getting-started.md">Browse</a></td></tr><tr><td><strong>Examples</strong></td><td>Runnable samples for evaluations, judges, traces, models, public catalog.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/examples/README.md">Browse</a></td></tr><tr><td><strong>Security</strong></td><td>API key management, data privacy, environment variables, rate limiting.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/security/README.md">Browse</a></td></tr><tr><td><strong>Troubleshooting</strong></td><td>Authentication, common issues, error codes reference.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/troubleshooting/README.md">Browse</a></td></tr></tbody></table>

## Where to next

* [Client configuration](https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/client.md)
* [Cookbook](/2.-get-started/all-cookbook-recipes.md)
* [Samples](/2.-get-started/samples-overview.md)
* [API reference (REST)](/13.1-sdk-and-apis/api.md)
* [Source on GitHub](https://github.com/layerlens/stratix-python)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.layerlens.ai/6.-build-wire-your-code/sdk-python.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.