LLM Tracekit
Open-source observability for your LLM application, based on OpenTelemetry.
LLM Tracekit is a set of OpenTelemetry instrumentations that gives you complete observability over your LLM application. Because it uses OpenTelemetry under the hood, it can be connected to your existing observability solutions - Coralogix, Datadog, Honeycomb, and others.
🚀 Getting Started
Install the instrumentation for your LLM provider:
pip install llm-tracekit-openai # For OpenAI
pip install llm-tracekit-bedrock # For AWS Bedrock
pip install llm-tracekit-gemini # For Google Gemini
pip install llm-tracekit-google-adk # For Google ADK
pip install llm-tracekit-litellm # For LiteLLM
pip install llm-tracekit-langchain # For LangChain
pip install llm-tracekit-langgraph # For LangGraph
pip install llm-tracekit-openai-agents # For OpenAI Agents SDK
pip install llm-tracekit-strands # For Strands Agents
pip install llm-tracekit-anthropic # For Anthropic (Claude API)
pip install llm-tracekit-microsoft-foundry # For Microsoft Foundry
Then instrument your code:
from llm_tracekit.openai import OpenAIInstrumentor, setup_export_to_coralogix
setup_export_to_coralogix(
service_name="my-ai-service",
capture_content=True,
)
OpenAIInstrumentor().instrument()
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Hello!"}],
)
🪗 What do we instrument?
LLM Providers
| Provider | Package | Instrumentor |
|---|---|---|
| OpenAI | llm-tracekit-openai |
OpenAIInstrumentor |
| AWS Bedrock | llm-tracekit-bedrock |
BedrockInstrumentor |
| Google Gemini | llm-tracekit-gemini |
GeminiInstrumentor |
| Anthropic | llm-tracekit-anthropic |
AnthropicInstrumentor |
| Microsoft Foundry | llm-tracekit-microsoft-foundry |
MicrosoftFoundryInstrumentor |
Frameworks
| Framework | Package | Instrumentor |
|---|---|---|
| Google ADK | llm-tracekit-google-adk |
GoogleADKInstrumentor |
| LiteLLM | llm-tracekit-litellm |
LiteLLMInstrumentor |
| LangChain | llm-tracekit-langchain |
LangChainInstrumentor |
| LangGraph | llm-tracekit-langgraph |
LangGraphInstrumentor |
| OpenAI Agents SDK | llm-tracekit-openai-agents |
OpenAIAgentsInstrumentor |
| Strands Agents | llm-tracekit-strands |
StrandsInstrumentor |
📖 Usage
Setting up tracing
Export to Coralogix
from llm_tracekit.openai import setup_export_to_coralogix
setup_export_to_coralogix(
service_name="ai-service",
application_name="ai-application",
subsystem_name="ai-subsystem",
capture_content=True,
)
🛡️ Guardrails
LLM Tracekit also includes Coralogix Guardrails - a client for protecting your LLM applications with content moderation, PII detection, prompt injection detection, and more.
See the Guardrails documentation for details.
📚 Documentation
For detailed documentation on each instrumentation, see the individual READMEs:
- OpenAI
- AWS Bedrock
- Google Gemini
- Google ADK
- LiteLLM
- LangChain
- LangGraph
- OpenAI Agents SDK
- Strands Agents
- Anthropic
- Microsoft Foundry
📜 License
Apache 2.0 - See LICENSE for details.
Metadata
Release files for llm-tracekit 2.9.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| llm_tracekit-2.9.0-py3-none-any.whl | Python 3 | none | any | Details for llm_tracekit-2.9.0-py3-none-any.whl |
Release files / llm_tracekit-2.9.0-py3-none-any.whl
| Download URL | llm_tracekit-2.9.0-py3-none-any.whl |
|---|---|
| Size | 6.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
9cb25f124ae8736b27cbb42352b5a1c8f915b0e823ee0e0ceff76f4f88464203
|
|
BLAKE2b-256 checksum How to use checksums |
04830c741cca6af68523fe68429ac81f7472191bb2b196497c4e52e391484ee7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.27 {"installer":{"name":"uv","version":"0.11.27","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for llm-tracekit 2.9.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.