lmnr
Python SDK for Laminar
Decision gist · record as of 2026-08-14
Yes. The package is actively maintained, has low install friction, carries a permissive Apache-2.0 license, and has no known vulnerabilities. It solves a real problem—observability for LLM applications—and integrates with popular LLM libraries. Install it if you need tracing and evaluation for LLM products and have access to a Laminar backend; skip it if you have no observability backend or prefer a different platform.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later (supports up to 3.14).
- Laminar backend must be accessible and a valid project API key must be provided.
- Low friction install with a pure-Python wheel.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions—suitable for most production environments.
last release 2026-08-11 (3 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 36,118,188 downloads/mo, #736 on PyPI
Alternatives
Verify before relying
pip install lmnr
from lmnr import Laminar
Laminar.initialize(project_api_key="<PROJECT_API_KEY>")- Performance overhead of automatic instrumentation on latency-sensitive LLM applications
- Data retention and privacy guarantees for traces sent to backend
- Specific LLM library version compatibility beyond OpenTelemetry instrumentation support
What it is and what it does
This is a Python SDK that integrates your LLM application with Laminar, an open-source platform for engineering LLM products. It provides two complementary ways to capture application behavior: automatic instrumentation of popular LLM libraries through OpenTelemetry, and manual instrumentation via decorators and context managers for custom code. Once initialized with a project API key, the SDK sends traces to a Laminar backend where you can review, evaluate, and annotate LLM interactions.
The package depends on OpenTelemetry's SDK and exporter components (both HTTP and gRPC variants), httpx for HTTP operations, and utility libraries including pydantic, orjson, and tenacity. It supports Python 3.10 through 3.14 and is designed to be initialized once at application startup. The SDK also provides an evaluation framework for running local assessments of LLM outputs against custom scoring functions, and a client interface for interacting with Laminar's API endpoints.
Use it for
- Automatically capture traces of LLM API calls within your application without modifying existing code
- Manually instrument custom functions and request handlers to track multi-step workflows and identify bottlenecks
- Run local evaluations of LLM outputs against custom metrics and compare results across feature iterations
- Self-host Laminar and use the SDK to send traces to your own infrastructure for compliance requirements
- Stream execution steps and outputs from Laminar's agent endpoint for real-time monitoring
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is actively maintained, has low install friction, carries a permissive Apache-2.0 license, and has no known vulnerabilities. It solves a real problem—observability for LLM applications—and integrates with popular LLM libraries. Install it if you need tracing and evaluation for LLM products and have access to a Laminar backend; skip it if you have no observability backend or prefer a different platform.
Install
lmnr on PyPI
Before you install
Low friction install with a pure-Python wheel. Active maintenance with a release 3 days old. Depends on 18 runtime packages including OpenTelemetry components, gRPC, and common utilities—a substantial but standard dependency footprint for observability tooling.
Requires Python 3.10 or later (supports up to 3.14). Laminar backend must be accessible and a valid project API key must be provided.
License in practice
Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions—suitable for most production environments.
Quickstart
pip install lmnr
from lmnr import Laminar
Laminar.initialize(project_api_key="<PROJECT_API_KEY>")Verify before relying
- Performance overhead of automatic instrumentation on latency-sensitive LLM applications
- Data retention and privacy guarantees for traces sent to backend
- Specific LLM library version compatibility beyond OpenTelemetry instrumentation support
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <4,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 18 packagesblake3grpciohttpxlmnr-claude-code-proxyopentelemetry-apiopentelemetry-sdkopentelemetry-exporter-otlp-proto-httpopentelemetry-exporter-otlp-proto-grpcopentelemetry-instrumentationopentelemetry-instrumentation-threadingopentelemetry-semantic-conventionsopentelemetry-semantic-conventions-aiorjsonpackagingpydanticpython-dotenvtqdmtenacity |
| Maintenance | Actively maintained 3 days since the last release |
| First released | |
| Downloads | 36,118,188 / month, #736 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14 |
Evidence: lmnr-0.7.59-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “trace evaluate annotate llm”
- lmnrPython SDK that traces, evaluates, and analyzes LLM application…
- trulensTruLens instruments LLM applications to trace execution step-by-step,…
- opentelemetry-instrumentation-togetherAutomatically traces calls to Together AI's API endpoints by…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also traceloop-sdk · aliyun-trace · opentelemetry-instrumentation-writer · trulens · opentelemetry-instrumentation-llamaindex · opentelemetry-instrumentation-openai · opentelemetry-instrumentation-groq · opentelemetry-instrumentation-ollama · opentelemetry-instrumentation-anthropic · lmnr-claude-code-proxy