# OpenLIT

## Docs

- [OpenLIT](https://mintlify.wiki/openlit/openlit/introduction.md): Open-source AI engineering platform — observability, evaluations, guardrails, prompt management, and GPU monitoring for LLMs and AI applications.
- [API reference](https://mintlify.wiki/openlit/openlit/openlit/api/introduction.md): Authenticate and call the OpenLIT REST API to retrieve prompts and secrets programmatically
- [Configuration](https://mintlify.wiki/openlit/openlit/openlit/configuration.md): Environment variables for configuring your OpenLIT deployment
- [Dashboards](https://mintlify.wiki/openlit/openlit/openlit/dashboards/overview.md): Build interactive dashboards to monitor AI application performance, visualize telemetry data, and explore LLM operations in real time
- [LLM-as-a-judge](https://mintlify.wiki/openlit/openlit/openlit/evaluations/llm-as-a-judge.md): Automatically evaluate production LLM traces for quality and safety — no code changes required
- [Evaluations overview](https://mintlify.wiki/openlit/openlit/openlit/evaluations/overview.md): Automated eval scoring, hallucination detection, bias monitoring, and toxicity analysis for LLM applications
- [Programmatic evaluations](https://mintlify.wiki/openlit/openlit/openlit/evaluations/programmatic.md): Run hallucination, bias, and toxicity evaluations directly from Python code using the OpenLIT SDK
- [OpenGround](https://mintlify.wiki/openlit/openlit/openlit/experiments/openground.md): Compare multiple LLMs side-by-side on cost, response time, and output quality using OpenLIT's built-in playground
- [Deploy OpenLIT](https://mintlify.wiki/openlit/openlit/openlit/installation.md): Self-host OpenLIT with Docker Compose or Kubernetes using Helm
- [Exceptions monitoring](https://mintlify.wiki/openlit/openlit/openlit/observability/errors.md): View, filter, and debug all error traces from your AI applications in one place.
- [Fleet Hub](https://mintlify.wiki/openlit/openlit/openlit/observability/fleet-hub.md): Centrally manage and monitor all your OpenTelemetry Collectors using the OpAMP protocol, directly from the OpenLIT UI.
- [Metrics](https://mintlify.wiki/openlit/openlit/openlit/observability/metrics.md): Visualize OpenTelemetry metrics from your AI applications using OpenLIT dashboards.
- [Tracing](https://mintlify.wiki/openlit/openlit/openlit/observability/tracing.md): View and analyze distributed traces from your AI applications in OpenLIT.
- [Prompt Hub](https://mintlify.wiki/openlit/openlit/openlit/prompts/prompt-hub.md): Centrally manage, version, and deploy prompts — then retrieve them at runtime using the SDK or REST API
- [Quickstart](https://mintlify.wiki/openlit/openlit/openlit/quickstart.md): Get LLM observability running in under 5 minutes
- [Vault](https://mintlify.wiki/openlit/openlit/openlit/secrets/vault.md): Centrally store and retrieve LLM API keys and other secrets without embedding them in code or environment variables
- [Operator configuration](https://mintlify.wiki/openlit/openlit/operator/configuration.md): Configure the OpenLIT Operator deployment with Helm values, and define AutoInstrumentation custom resources to control how workloads are instrumented.
- [Destinations](https://mintlify.wiki/openlit/openlit/operator/destinations.md): Configure where the OpenLIT Operator sends AI telemetry — traces, metrics, and logs — by setting the OTLP endpoint and optional authentication headers in your AutoInstrumentation resource.
- [Install the operator](https://mintlify.wiki/openlit/openlit/operator/installation.md): Deploy the OpenLIT Operator to your Kubernetes cluster using Helm, verify the installation, and keep it up to date.
- [Instrumentations](https://mintlify.wiki/openlit/openlit/operator/instrumentations.md): Annotate Kubernetes Deployments for automatic Python instrumentation and choose from OpenLIT, OpenInference, OpenLLMetry, or a custom provider.
- [Kubernetes Operator](https://mintlify.wiki/openlit/openlit/operator/overview.md): Automatically inject OpenTelemetry AI instrumentation into Kubernetes workloads without modifying pod specs, container images, or application code.
- [Operator quickstart](https://mintlify.wiki/openlit/openlit/operator/quickstart.md): Deploy the OpenLIT Operator and instrument a sample AI Agent in 5 minutes, with zero code changes.
- [SDK configuration](https://mintlify.wiki/openlit/openlit/sdk/configuration.md): All parameters for openlit.init() with their types, defaults, and environment variable equivalents.
- [Send to Datadog](https://mintlify.wiki/openlit/openlit/sdk/destinations/datadog.md): Configure the OpenLIT SDK to send AI observability data to Datadog via the Datadog Agent OTLP receiver
- [Send to Grafana Cloud](https://mintlify.wiki/openlit/openlit/sdk/destinations/grafana.md): Configure the OpenLIT SDK to send AI observability data to Grafana Cloud using the OTLP gateway
- [Send to OpenLIT](https://mintlify.wiki/openlit/openlit/sdk/destinations/openlit.md): Configure the OpenLIT SDK to send traces and metrics to a self-hosted OpenLIT platform instance
- [Destinations overview](https://mintlify.wiki/openlit/openlit/sdk/destinations/overview.md): Send AI observability data from OpenLIT to your existing observability stack using standard OTLP
- [Cost tracking](https://mintlify.wiki/openlit/openlit/sdk/features/cost-tracking.md): Automatic per-call LLM cost calculation with support for custom pricing for fine-tuned and private models.
- [Evaluations](https://mintlify.wiki/openlit/openlit/sdk/features/evaluations.md): Programmatic scoring of LLM outputs for hallucination, bias, and toxicity using the OpenLIT SDK.
- [GPU monitoring](https://mintlify.wiki/openlit/openlit/sdk/features/gpu.md): Collect GPU utilization, memory, temperature, and power metrics from NVIDIA and AMD GPUs alongside your LLM traces.
- [Guardrails](https://mintlify.wiki/openlit/openlit/sdk/features/guardrails.md): Real-time content safety checks for prompt injection, sensitive topics, and topic restriction.
- [Tracing](https://mintlify.wiki/openlit/openlit/sdk/features/tracing.md): Automatic and manual distributed tracing for LLM calls, agent workflows, and the full request path.
- [AI framework integrations](https://mintlify.wiki/openlit/openlit/sdk/integrations/ai-frameworks.md): Trace agent execution, tool calls, chains, and memory operations across LangChain, LlamaIndex, CrewAI, and 15+ more AI frameworks
- [GPU integrations](https://mintlify.wiki/openlit/openlit/sdk/integrations/gpu.md): Monitor NVIDIA and AMD GPU utilization, memory, temperature, and power consumption with OpenTelemetry
- [LLM provider integrations](https://mintlify.wiki/openlit/openlit/sdk/integrations/llm-providers.md): Auto-instrument OpenAI, Anthropic, Cohere, Mistral, Groq, AWS Bedrock, and 20+ more LLM providers with zero code changes
- [Integrations overview](https://mintlify.wiki/openlit/openlit/sdk/integrations/overview.md): Auto-instrument 60+ LLM providers, AI frameworks, and vector databases with a single openlit.init() call
- [Vector database integrations](https://mintlify.wiki/openlit/openlit/sdk/integrations/vector-databases.md): Auto-instrument ChromaDB, Pinecone, Qdrant, Milvus, Astra DB, and PostgreSQL vector operations with OpenTelemetry
- [SDK overview](https://mintlify.wiki/openlit/openlit/sdk/overview.md): OpenTelemetry-native AI observability for Python, TypeScript, and Go — with zero code changes required.
- [SDK quickstart](https://mintlify.wiki/openlit/openlit/sdk/quickstart.md): Get from zero to your first AI trace in three steps.