> ## Documentation Index > Fetch the complete documentation index at: https://mintlify.com/openlit/openlit/llms.txt > Use this file to discover all available pages before exploring further. # OpenLIT > Open-source AI engineering platform — observability, evaluations, guardrails, prompt management, and GPU monitoring for LLMs and AI applications. OpenLIT is an open-source AI engineering platform that helps teams build, evaluate, and observe AI applications across the entire lifecycle — from development to production. It provides **OpenTelemetry-native** auto-instrumentation for 50+ LLM providers, AI frameworks, vector databases, and GPUs with a single line of code. Self-host with Docker Compose or Kubernetes Helm in minutes Get LLM observability running in under 5 minutes Python, TypeScript, and Go SDKs with zero-code instrumentation 50+ LLM providers, frameworks, and vector databases ## What is OpenLIT? OpenLIT provides three interconnected OSS tools: Full-stack platform for tracing, dashboards, prompt management, evaluations, and secrets management OpenTelemetry-native auto-instrumentation SDKs for Python, TypeScript, and Go Automatically inject instrumentation into AI workloads without code changes ## Key features Distributed tracing and metrics for every LLM call — latency, cost, token usage, and errors Real-time NVIDIA and AMD GPU utilization, memory, temperature, and power metrics LLM-as-a-judge and programmatic evaluations to measure response quality in production Real-time prompt injection detection, topic restrictions, and sensitive data protection Version, manage, and deploy prompts across environments without code changes Centrally store LLM API keys — applications retrieve them remotely at runtime Compare cost, latency, and quality across LLMs side-by-side in a playground Build dashboards with flexible widgets and custom SQL queries over your telemetry data ## How it works ```mermaid theme={null} flowchart LR subgraph "Your Application" A[AI Code] -->|openlit.init| B[OpenLIT SDK] end B -->|OTLP Traces & Metrics| C[OpenTelemetry Collector] C -->|Stores Data| D[ClickHouse] E[OpenLIT UI] -->|Queries| D ``` Run the OpenLIT stack with Docker Compose — includes the UI, ClickHouse database, and OpenTelemetry Collector. ```bash theme={null} git clone https://github.com/openlit/openlit.git cd openlit docker compose up -d ``` Install the OpenLIT Python SDK from PyPI. ```bash theme={null} pip install openlit ``` Add two lines to your existing AI application — OpenLIT auto-detects and instruments all supported libraries. ```python theme={null} import openlit openlit.init(otlp_endpoint="http://127.0.0.1:4318") ``` Open `http://127.0.0.1:3000` and log in with the default credentials (`user@openlit.io` / `openlituser`) to explore traces, metrics, and dashboards. ## Supported integrations OpenLIT auto-instruments 50+ integrations across LLM providers, AI frameworks, and vector databases: **LLM Providers** — OpenAI, Anthropic, Cohere, Mistral, Groq, AWS Bedrock, Google Vertex AI, Google AI Studio, Azure OpenAI, Ollama, vLLM, Hugging Face, DeepSeek, and more **AI Frameworks** — LangChain, LlamaIndex, CrewAI, OpenAI Agents SDK, Pydantic AI, AutoGen (AG2), Haystack, LiteLLM, Mem0, and more **Vector Databases** — Pinecone, ChromaDB, Qdrant, Milvus, Astra DB, PostgreSQL (pgvector) **GPUs** — NVIDIA (nvidia-smi), AMD (ROCm) Browse the full list of supported integrations with setup guides ## Open source OpenLIT is released under the [Apache 2.0 license](https://github.com/openlit/openlit/blob/main/LICENSE). It follows and maintains [OpenTelemetry Semantic Conventions](https://github.com/open-telemetry/semantic-conventions/tree/main/docs/gen-ai) for GenAI observability, consistently updating to align with the latest standards. Star the repo, report issues, and contribute Join the community for support and discussions