# OpenLIT

> OpenLIT is the leading open-source AI observability platform with zero-code instrumentation for LLMs, vector databases, and AI frameworks. Monitor OpenAI, Anthropic, LangChain, LlamaIndex with OpenTelemetry. Features include cost tracking, performance metrics, prompt management, and enterprise-grade security for production AI applications.

## Docs

- [Command Reference](https://docs.openlit.io/latest/cli/commands.md): Every openlit CLI command, subcommand, and flag
- [CLI Configuration](https://docs.openlit.io/latest/cli/configuration.md): Configure the openlit CLI - endpoint, API key, content capture, and precedence rules
- [Install the CLI](https://docs.openlit.io/latest/cli/installation.md): Install the openlit CLI on macOS, Linux, Windows, Docker, or from source
- [OpenLIT CLI](https://docs.openlit.io/latest/cli/overview.md): The command-line interface for OpenLIT - observe coding agents today, control the whole platform tomorrow
- [What is AI Evaluation?](https://docs.openlit.io/latest/glossary/what-is-ai-evaluation.md): AI evaluation explained: how LLM-as-a-judge scoring works, online vs. offline evaluation, and how to catch quality regressions
- [What is AI Observability?](https://docs.openlit.io/latest/glossary/what-is-ai-observability.md): AI observability explained: what it is, why it matters, and how to add it to LLM apps and agents with zero code changes
- [What is Prompt Engineering?](https://docs.openlit.io/latest/glossary/what-is-prompt-engineering.md): Prompt engineering explained: versioning, testing, and deploying prompts as managed, trackable artifacts
- [Configuration](https://docs.openlit.io/latest/gpu-collector/configuration.md): Environment variables reference for the OpenTelemetry GPU Collector
- [AMD GPUs](https://docs.openlit.io/latest/gpu-collector/gpus/amd.md): Monitor AMD GPU metrics via sysfs/hwmon using the OpenTelemetry GPU Collector
- [Intel GPUs](https://docs.openlit.io/latest/gpu-collector/gpus/intel.md): Monitor Intel GPU metrics via sysfs/hwmon using the OpenTelemetry GPU Collector
- [NVIDIA GPUs](https://docs.openlit.io/latest/gpu-collector/gpus/nvidia.md): Monitor NVIDIA GPU metrics via NVML using the OpenTelemetry GPU Collector
- [Installation](https://docs.openlit.io/latest/gpu-collector/installation.md): Install the OpenTelemetry GPU Collector via Docker, binary, or from source
- [Metrics Reference](https://docs.openlit.io/latest/gpu-collector/metrics.md): Complete list of all metrics exported by the OpenTelemetry GPU Collector
- [Overview](https://docs.openlit.io/latest/gpu-collector/overview.md): OpenTelemetry-native GPU and host metrics collector for NVIDIA, AMD, and Intel GPUs
- [Quickstart](https://docs.openlit.io/latest/gpu-collector/quickstart.md): Get the OpenTelemetry GPU Collector running in under 5 minutes
- [Chat with Otter](https://docs.openlit.io/latest/openlit/chat/conversations.md): Use Otter's AI chat assistant to query observability data with natural language, save widgets, generate dashboards, and manage OpenLIT resources
- [Overview](https://docs.openlit.io/latest/openlit/chat/overview.md): Otter is OpenLIT's AI chat assistant for observability - ask natural language questions about traces, costs, and tokens, and manage resources through conversation
- [Chat Settings](https://docs.openlit.io/latest/openlit/chat/settings.md): Configure Otter's AI Provider, Model, and Vault API key on the Chat Settings page before using the AI chat assistant
- [Otter usage](https://docs.openlit.io/latest/openlit/chat/usage.md): Track Otter AI chat assistant token and cost attribution by feature, provider, model, and date
- [Analytics](https://docs.openlit.io/latest/openlit/coding-agents/analytics.md): The seeded Coding Agents dashboard - sessions, cost, acceptance, top tools and repos, and session outcomes, scoped per vendor or per user
- [Overview](https://docs.openlit.io/latest/openlit/coding-agents/overview.md): OpenLIT ships first-class observability for AI coding agents - Claude Code, Cursor, Codex, and Windsurf - with no SDK and no code changes
- [Privacy & Governance](https://docs.openlit.io/latest/openlit/coding-agents/privacy-and-governance.md): Content capture modes, redaction, and attribution safeguards for coding-agent telemetry
- [Sessions](https://docs.openlit.io/latest/openlit/coding-agents/sessions.md): Every coding session for a vendor, with a full conversational drill-in per session
- [Setup & Configure](https://docs.openlit.io/latest/openlit/coding-agents/setup-and-configure.md): Install the openlit CLI, wire each vendor's hooks, then configure the endpoint, content capture, and stopping tracking
- [Troubleshooting](https://docs.openlit.io/latest/openlit/coding-agents/troubleshooting.md): Diagnose a missing row, silent hooks, or a stale database config for coding-agent telemetry
- [Users](https://docs.openlit.io/latest/openlit/coding-agents/users.md): Per-developer rollups of coding-agent activity, cost, and code impact
- [Configuration](https://docs.openlit.io/latest/openlit/configuration.md): Configuring Options for OpenLIT
- [Analytics](https://docs.openlit.io/latest/openlit/costs/analytics.md): AI cost analytics for LLM spend - cost by environment and application, Auto Pricing run history, and optimization charts by provider and model
- [Configuration](https://docs.openlit.io/latest/openlit/costs/configuration.md): AI cost tracking configuration - enable Auto Pricing on a schedule and recalculate LLM costs on individual traces from Monitor → Costs
- [Import and export](https://docs.openlit.io/latest/openlit/costs/manage-models/import-and-export.md): Import Pricing JSON into Manage Models or Export Pricing as SDK-compatible pricing.json - duplicates are skipped on import
- [Models](https://docs.openlit.io/latest/openlit/costs/manage-models/models.md): Browse and edit LLM model pricing in Manage Models - Model ID, type, context window, and input/output price per 1M tokens
- [Overview](https://docs.openlit.io/latest/openlit/costs/manage-models/overview.md): Manage models on the Costs page - edit LLM providers and per-model token prices used for AI cost tracking across traces, Otter, OpenGround, and the SDK
- [Providers](https://docs.openlit.io/latest/openlit/costs/manage-models/providers.md): Add and edit LLM providers in Manage Models - Provider ID, display name, description, and Requires API Key (Vault)
- [SDK pricing URL](https://docs.openlit.io/latest/openlit/costs/manage-models/sdk-pricing.md): Use Manage Models' public SDK Pricing URL in openlit.init() so LLM token pricing stays synced without shipping a local pricing.json
- [Overview](https://docs.openlit.io/latest/openlit/costs/overview.md): AI cost tracking and AI cost analytics in OpenLIT - monitor LLM spend, manage model pricing, and backfill missing costs from Monitor → Costs
- [Auto Refresh & Time Interval](https://docs.openlit.io/latest/openlit/dashboards/auto-refresh-and-time-interval.md): Learn how to enable auto-refresh and set time intervals in OpenLIT dashboards to keep your data live and updated in real time.
- [Create Dashboard](https://docs.openlit.io/latest/openlit/dashboards/create-dashboard.md): Learn how to create dashboards in OpenLIT with step-by-step instructions for adding widgets, configuring visualizations, and building effective monitoring visualizations.
- [Create Folder](https://docs.openlit.io/latest/openlit/dashboards/create-folder.md): Create folders to organize dashboards into logical collections by team, feature, environment, or product for better management and navigation.
- [Export Dashboard](https://docs.openlit.io/latest/openlit/dashboards/export-dashboard.md): Learn how to export your OpenLIT dashboards for backup, sharing, and migration across different environments.
- [Filters & Dynamic Bindings](https://docs.openlit.io/latest/openlit/dashboards/filters-and-dynamic-bindings.md): Learn how to make OpenLIT dashboards interactive by using filters and mustache-style dynamic bindings inside ClickHouse queries.
- [Import Dashboard](https://docs.openlit.io/latest/openlit/dashboards/import-dashboard.md): Learn how to import pre-built dashboard layouts in OpenLIT to quickly set up comprehensive monitoring views for your AI applications.
- [Organize Dashboards](https://docs.openlit.io/latest/openlit/dashboards/organize-dashboards.md): Learn how to organize dashboards in OpenLIT using folders, boards, and drag-and-drop for better structure and navigation.
- [Overview](https://docs.openlit.io/latest/openlit/dashboards/overview.md): Create powerful, interactive dashboards to monitor AI application performance, visualize telemetry data, and gain insights into your LLM operations with real-time analytics.
- [Pin a Dashboard](https://docs.openlit.io/latest/openlit/dashboards/pin-dashboard.md): Learn how to pin a dashboard in OpenLIT to keep key dashboards easily accessible at the top of your list.
- [Set a Main Dashboard](https://docs.openlit.io/latest/openlit/dashboards/set-main-dashboard.md): Learn how to set a dashboard as your main (home) dashboard in OpenLIT for faster access to your most important views.
- [Area Chart Widget](https://docs.openlit.io/latest/openlit/dashboards/widgets/area-chart-widget.md): Learn how to use the Area Chart Widget in OpenLIT to visualize time-based trends using ClickHouse queries and dynamic parameters.
- [Bar Chart Widget](https://docs.openlit.io/latest/openlit/dashboards/widgets/bar-chart-widget.md): Learn how to use the Bar Chart Widget in OpenLIT to compare grouped data using ClickHouse queries and dynamic filters.
- [Line Chart Widget](https://docs.openlit.io/latest/openlit/dashboards/widgets/line-chart-widget.md): Learn how to use the Line Chart Widget in OpenLIT to plot precise time series metrics using ClickHouse queries and dynamic bindings.
- [Markdown Widget](https://docs.openlit.io/latest/openlit/dashboards/widgets/markdown-widget.md): Learn how to use the Markdown Widget in OpenLIT to add rich text, annotations, and links to your dashboards.
- [Overview](https://docs.openlit.io/latest/openlit/dashboards/widgets/overview.md): Learn about OpenLIT's widget system for creating powerful data visualizations, from time series charts to statistical summaries and interactive tables.
- [Pie Chart Widget](https://docs.openlit.io/latest/openlit/dashboards/widgets/pie-chart-widget.md): Learn how to use the Pie Chart Widget in OpenLIT to display proportions and segment distributions using ClickHouse data.
- [Stats Widget](https://docs.openlit.io/latest/openlit/dashboards/widgets/stat-widget.md): Learn how to use the Statistics Widget in OpenLIT to display key metrics, KPIs, and summary values with real-time ClickHouse data.
- [Table Widget](https://docs.openlit.io/latest/openlit/dashboards/widgets/table-widget.md): Learn how to use the Table Widget in OpenLIT to display structured data with sorting, scrolling, and pagination using ClickHouse queries.
- [Anonymous Usage Metrics](https://docs.openlit.io/latest/openlit/developer-resources/anonymous-telemetry.md): How OpenLIT's anonymous usage metrics work, what is collected, and how to opt out of telemetry with TELEMETRY_ENABLED=false
- [Export Pricing](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/manage-models/export.md): Returns pricing grouped by model type (chat, embeddings, images, audio) in OpenLIT SDK pricing_json shape.
- [Import Pricing](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/manage-models/import.md): Accepts a structured providers and models payload, or the SDK pricing_json object shape keyed by model type (chat, embeddings, and so on).
- [Models](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/manage-models/models.md): Returns models grouped by provider. Optional `provider` query filters to one provider.
- [Providers](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/manage-models/providers.md): Returns providers with supported models. Optional `provider` or `search` query params.
- [Public pricing export](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/manage-models/public-pricing.md): Returns SDK-compatible pricing for all models in that database config. No auth. Cached for 5 minutes.
- [Get Prompt](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/prompt-hub/get.md): Fetches a compiled prompt using the provided prompt ID, version, and variables.
- [Evaluate Rules](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/rule-engine/evaluate.md): Evaluates all active rules against the provided input fields and returns matching rule IDs, linked entities, and optionally their full data.
- [Get Secret(s)](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/vault/get.md): Fetches secret(s) using the provided key or tags.
- [Introduction](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/introduction.md): OpenAPI specification for API Endpoints in OpenLIT
- [Connect Multiple Databases](https://docs.openlit.io/latest/openlit/developer-resources/multiple-db.md): Connect multiple ClickHouse database configurations in one OpenLIT project and switch which one powers traces, dashboards, Prompt Hub, and Vault
- [Manage Secrets](https://docs.openlit.io/latest/openlit/developer-resources/vault/manage-secrets.md): Create, edit, tag, and delete secrets from the Vault list page
- [Overview](https://docs.openlit.io/latest/openlit/developer-resources/vault/overview.md): Securely manage LLM API keys and other secrets in one place, then retrieve them at runtime from any application via SDK or API
- [Retrieve Secrets](https://docs.openlit.io/latest/openlit/developer-resources/vault/retrieve-secrets.md): Fetch Vault secrets into your application with the Python or TypeScript SDK, or the REST API
- [Security](https://docs.openlit.io/latest/openlit/developer-resources/vault/security.md): Encryption at rest, per-user access, and CORS for browser-based secret retrieval
- [Analytics](https://docs.openlit.io/latest/openlit/evaluations/analytics.md): LLM evaluation analytics - pass rates, executions, total cost, and per-evaluator results under Monitor → Evaluations
- [Configuration](https://docs.openlit.io/latest/openlit/evaluations/configuration.md): Configure the LLM evaluation engine, Vault API key, Auto Evaluation schedule, and sample rate under Monitor → Evaluations
- [Evaluators](https://docs.openlit.io/latest/openlit/evaluations/evaluators.md): Enable built-in LLM evaluation types or create custom evaluators for hallucination, bias, toxicity, and your own criteria
- [LLM-as-a-Judge](https://docs.openlit.io/latest/openlit/evaluations/llm-as-a-judge.md): Use LLMs to evaluate AI application quality, safety, and performance with automated scoring and detailed analysis
- [Manual Feedback](https://docs.openlit.io/latest/openlit/evaluations/manual-feedback.md): Add human feedback - good, bad, or neutral, with an optional comment - directly on a trace
- [Overview](https://docs.openlit.io/latest/openlit/evaluations/overview.md): LLM evaluation in OpenLIT - AI evals for hallucination, bias, toxicity, and custom criteria under Monitor → Evaluations
- [Programmatic Evaluations](https://docs.openlit.io/latest/openlit/evaluations/programmatic-evals.md): Quickly evaluate your LLMs and AI Agent responses for Hallucination, Bias, and Toxicity
- [Self-Host OpenLIT](https://docs.openlit.io/latest/openlit/installation.md): Self-host OpenLIT with Docker or Kubernetes. Deploy OpenLIT, ClickHouse, and an OpenTelemetry Collector on your own infrastructure.
- [OAuth](https://docs.openlit.io/latest/openlit/oauth.md): Configure Google and GitHub OAuth authentication for OpenLIT using NextAuth.js
- [Analytics](https://docs.openlit.io/latest/openlit/observability/agents/analytics.md): The Dashboard tab - an agent's own latency, cost, token usage, and error rate over time
- [Configuration](https://docs.openlit.io/latest/openlit/observability/agents/configuration.md): Toggle LLM Observability and Agent Observability for an already-discovered agent
- [Definition](https://docs.openlit.io/latest/openlit/observability/agents/definition.md): The system prompt and tools captured for an agent's currently selected version
- [Monitoring](https://docs.openlit.io/latest/openlit/observability/agents/monitoring.md): The Monitoring tab - this agent's own traces and requests, filtered down from the Telemetry page's trace list
- [Overview](https://docs.openlit.io/latest/openlit/observability/agents/overview.md): AI agent observability, built entirely from OpenTelemetry trace data - discover every agent and its live call graph with zero registration
- [Setup](https://docs.openlit.io/latest/openlit/observability/agents/setup.md): What it takes for an agent to show up on the Agents page - zero code by default, explicit identity when you want it
- [Versioning](https://docs.openlit.io/latest/openlit/observability/agents/versioning.md): Trace-derived config snapshots, and exactly how selecting one scopes each tab on the agent detail page
- [AI Analysis](https://docs.openlit.io/latest/openlit/observability/telemetry/ai-analysis.md): Turn a trace or span into a structured, AI-generated review of performance, reliability, cost, and token efficiency
- [Logs](https://docs.openlit.io/latest/openlit/observability/telemetry/logs.md): A searchable, filterable explorer for OTel log records ingested through OpenLIT's built-in OpenTelemetry Collector
- [Metrics](https://docs.openlit.io/latest/openlit/observability/telemetry/metrics.md): A dedicated explorer for every OTel metric OpenLIT has received, with a trend chart and data-point detail per metric
- [Overview](https://docs.openlit.io/latest/openlit/observability/telemetry/overview.md): LLM observability for traces, metrics, logs, and exceptions - all in one Telemetry page, built on OpenTelemetry
- [Traces & Exceptions](https://docs.openlit.io/latest/openlit/observability/telemetry/traces.md): Filter and group traces, then drill into a five-view trace detail explorer with span attributes, chat view, timeline, and DAG
- [Database Config](https://docs.openlit.io/latest/openlit/organisation/database-config.md): Add and manage ClickHouse database configurations for an OpenLIT project
- [Organisation Overview](https://docs.openlit.io/latest/openlit/organisation/overview.md): Understand how organisations, projects, and database configurations fit together in OpenLIT
- [Projects](https://docs.openlit.io/latest/openlit/organisation/projects.md): Create and manage project boundaries inside an OpenLIT organisation
- [Link Rules](https://docs.openlit.io/latest/openlit/prompts-experiments/context/link-rules.md): Connect a context to Rule Engine rules from either the context's detail page or the rule's detail page
- [Manage Contexts](https://docs.openlit.io/latest/openlit/prompts-experiments/context/manage-contexts.md): Create, edit, and delete contexts - name, description, markdown content, status, tags, and meta properties
- [Overview](https://docs.openlit.io/latest/openlit/prompts-experiments/context/overview.md): RAG context management for OpenLIT - store reusable content once and have the Rule Engine return the right piece automatically
- [Retrieve Context](https://docs.openlit.io/latest/openlit/prompts-experiments/context/retrieve-context.md): Fetch matching context content at runtime using the Rule Engine's evaluate API
- [Overview](https://docs.openlit.io/latest/openlit/prompts-experiments/openground/overview.md): OpenGround is OpenLIT's AI model comparison tool - an LLM playground for running one prompt across many providers at once and comparing cost, speed, and quality
- [Results & History](https://docs.openlit.io/latest/openlit/prompts-experiments/openground/results-and-history.md): Read the metrics overview, response-time waterfall, and cost breakdown for a run, then find, reopen, or reload it later from history
- [Run a Comparison](https://docs.openlit.io/latest/openlit/prompts-experiments/openground/run-a-comparison.md): Configure a prompt, select providers, tune per-provider settings, and evaluate on the /openground/new page
- [AI Prompt Improvement](https://docs.openlit.io/latest/openlit/prompts-experiments/prompt-hub/ai-improvement.md): Let Otter review a prompt and suggest targeted edits directly in the create and edit editors
- [Manage Prompts](https://docs.openlit.io/latest/openlit/prompts-experiments/prompt-hub/manage-prompts.md): Create, edit, tag, and delete prompts from the Prompt Hub list and detail pages
- [Overview](https://docs.openlit.io/latest/openlit/prompts-experiments/prompt-hub/overview.md): Prompt Hub is OpenLIT's prompt management platform for versioning, publishing, and fetching prompts with dynamic variables at runtime
- [Retrieve a Prompt](https://docs.openlit.io/latest/openlit/prompts-experiments/prompt-hub/retrieve-a-prompt.md): Fetch a saved prompt by name or ID, optionally a specific version, and compile it with dynamic variables via the SDK or API
- [Rules](https://docs.openlit.io/latest/openlit/prompts-experiments/prompt-hub/rules.md): Link a prompt to Rule Engine rules so it's returned automatically when a rule matches at evaluation time
- [Versioning](https://docs.openlit.io/latest/openlit/prompts-experiments/prompt-hub/versioning.md): Drafts vs. published versions, semantic versioning, and what the Versions tab shows
- [Conditions](https://docs.openlit.io/latest/openlit/prompts-experiments/rule-engine/conditions.md): Build condition groups on a rule's detail page - pick fields and operators from dropdowns, and combine groups with AND/OR
- [Create & Manage Rules](https://docs.openlit.io/latest/openlit/prompts-experiments/rule-engine/create-and-manage-rules.md): Create a rule from the Rule Engine list page, edit its details, and delete rules you no longer need
- [Evaluate API](https://docs.openlit.io/latest/openlit/prompts-experiments/rule-engine/evaluate-api.md): Call the Rule Engine evaluate endpoint from any application with a Bearer API key to retrieve resources linked to matching rules
- [Linked Entities](https://docs.openlit.io/latest/openlit/prompts-experiments/rule-engine/linked-entities.md): Connect a rule to a Context, Prompt, or Evaluation Type so matching returns real resources
- [Overview](https://docs.openlit.io/latest/openlit/prompts-experiments/rule-engine/overview.md): Rule Engine is a rules engine for conditional AI resource retrieval - define matching conditions once, and let your application or OpenLIT ask what applies right now
- [Preview](https://docs.openlit.io/latest/openlit/prompts-experiments/rule-engine/preview.md): Use the Rule Preview card on a rule's detail page to test its saved conditions against recent traces before relying on it
- [Get started with AI Observability](https://docs.openlit.io/latest/openlit/quickstart-ai-observability.md): Start monitoring your AI applications with the OpenLIT SDK in a few steps
- [Evaluations](https://docs.openlit.io/latest/openlit/quickstart-evals.md): Score AI outputs automatically for hallucination, bias, toxicity, and more - or add your own human feedback
- [OpenLIT Overview](https://docs.openlit.io/latest/overview.md): OpenLIT is an open-source AI Engineering platform for LLM observability, evaluations, prompt management, and cost tracking - built on OpenTelemetry, fully self-hostable.
- [Configuration](https://docs.openlit.io/latest/sdk/configuration.md): Configure the OpenLIT SDK for OpenTelemetry-native LLM observability, cost tracking, and performance monitoring
- [Dash0](https://docs.openlit.io/latest/sdk/destinations/dash0.md): Send OpenLIT AI observability traces and metrics to Dash0, an OpenTelemetry-native platform, for real-time LLM monitoring
- [DataDog](https://docs.openlit.io/latest/sdk/destinations/datadog.md): Export OpenLIT AI observability data to Datadog for unified LLM and infrastructure monitoring in one dashboard
- [Dynatrace](https://docs.openlit.io/latest/sdk/destinations/dynatrace.md): Send OpenLIT AI observability traces and metrics to Dynatrace for enterprise full-stack LLM monitoring
- [Elastic](https://docs.openlit.io/latest/sdk/destinations/elastic.md): Send OpenLIT AI observability data to Elastic Observability for search-powered LLM trace and log analysis
- [Grafana Cloud](https://docs.openlit.io/latest/sdk/destinations/grafanacloud.md): Send OpenLIT AI observability traces and metrics to Grafana Cloud to view LLM data alongside your existing Grafana dashboards
- [Highlight.io](https://docs.openlit.io/latest/sdk/destinations/highlight.md): Send OpenLIT AI observability data to Highlight.io, an open-source platform, for LLM monitoring alongside session replay
- [HyperDX](https://docs.openlit.io/latest/sdk/destinations/hyperdx.md): Send OpenLIT AI observability data to HyperDX, an open-source ClickHouse-backed platform, for unified LLM traces, logs, and metrics
- [Langfuse](https://docs.openlit.io/latest/sdk/destinations/langfuse.md): Send OpenLIT AI observability traces to Langfuse via OpenTelemetry for LLM-specific analytics and evaluation
- [Middleware](https://docs.openlit.io/latest/sdk/destinations/middleware.md): Send OpenLIT AI observability data to Middleware.io for full-stack LLM and infrastructure monitoring
- [Murnitur](https://docs.openlit.io/latest/sdk/destinations/murnitur.md): Send OpenLIT AI observability traces to Murnitur for LLM-focused monitoring and guardrails
- [New Relic](https://docs.openlit.io/latest/sdk/destinations/new-relic.md): Export OpenLIT AI observability data to New Relic for full-stack LLM monitoring alongside existing APM data
- [OneUptime](https://docs.openlit.io/latest/sdk/destinations/oneuptime.md): Send OpenLIT AI observability data to OneUptime, an open-source platform, for LLM monitoring with status pages and incidents
- [Oodle](https://docs.openlit.io/latest/sdk/destinations/oodle.md): Send OpenLIT AI observability data to Oodle for high-scale, cost-efficient LLM metrics and log storage
- [OpenLIT](https://docs.openlit.io/latest/sdk/destinations/openlit.md): Send SDK telemetry to the native OpenLIT platform for AI observability, cost tracking, and evaluation out of the box
- [OpenObserve](https://docs.openlit.io/latest/sdk/destinations/openobserve.md): Send OpenLIT AI observability data to OpenObserve, an open-source Rust-based platform, for cost-efficient LLM log and trace storage
- [OpenTelemetry Collector](https://docs.openlit.io/latest/sdk/destinations/otelcol.md): Route OpenLIT AI observability data through the OpenTelemetry Collector to any vendor-neutral telemetry backend
- [Overview](https://docs.openlit.io/latest/sdk/destinations/overview.md): Send AI observability data to your existing observability stack
- [Prometheus + Jaeger](https://docs.openlit.io/latest/sdk/destinations/prometheus-jaeger.md): Send OpenLIT AI observability data to Prometheus for LLM metrics and Jaeger for distributed tracing
- [Prometheus + Tempo](https://docs.openlit.io/latest/sdk/destinations/prometheus-tempo.md): Send OpenLIT AI observability data to Prometheus for LLM metrics and Grafana Tempo for distributed tracing
- [SigLens](https://docs.openlit.io/latest/sdk/destinations/siglens.md): Send OpenLIT AI observability data to SigLens, an open-source platform, for fast, cost-efficient LLM log search
- [SigNoz](https://docs.openlit.io/latest/sdk/destinations/signoz.md): Send OpenLIT AI observability data to SigNoz, an open-source OpenTelemetry-native platform, for all-in-one LLM monitoring
- [Victoria Stack](https://docs.openlit.io/latest/sdk/destinations/victoriametrics-stack.md): Send OpenLIT AI observability data to the VictoriaMetrics stack for high-performance, cost-efficient LLM metrics and logs
- [Custom Attributes](https://docs.openlit.io/latest/sdk/features/custom-attributes.md): Attach custom attributes to spans and metrics beyond OTEL_RESOURCE_ATTRIBUTES - globally, scoped to a block of code, or per agent
- [Evaluations](https://docs.openlit.io/latest/sdk/features/evaluations.md): Evaluate your LLM responses for hallucination, bias, toxicity, and more - using the same evals for dev and prod
- [GPU Performance Monitoring](https://docs.openlit.io/latest/sdk/features/gpu.md): Monitor NVIDIA and AMD GPUs with key metrics like usage, temperature, and power using OpenTelemetry for AI workloads
- [Guardrails](https://docs.openlit.io/latest/sdk/features/guardrails.md): Secure your app from Prompt Injection, Sensitive Topics, and Topic Restriction
- [Metrics](https://docs.openlit.io/latest/sdk/features/metrics.md): Visualize and monitor AI application metrics in OpenLIT platform with custom dashboards and advanced analytics
- [Track Cost for Custom Models](https://docs.openlit.io/latest/sdk/features/pricing.md): Use your own Pricing File to calculate LLM usage costs
- [Rule Engine](https://docs.openlit.io/latest/sdk/features/rule-engine.md): Evaluate rules and retrieve matching contexts, prompts, and evaluation configs from the OpenLIT Rule Engine
- [Distributed Tracing](https://docs.openlit.io/latest/sdk/features/tracing.md): Visualize and analyze distributed traces in OpenLIT platform with detailed span analysis and performance insights
- [Go SDK Overview](https://docs.openlit.io/latest/sdk/go-overview.md): OpenTelemetry-native observability for Go AI applications. Monitor OpenAI, Anthropic, and vLLM with automatic token tracking, cost calculation, and distributed tracing.
- [Instrumentation Methods](https://docs.openlit.io/latest/sdk/instrumentation-methods.md): Choose between zero-code instrumentation or manual instrumentation for AI observability
- [Monitor AutoGen using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/ag2.md): OpenLIT auto-instruments AutoGen (AG2) agents via OpenTelemetry, giving you AI observability and tracing into multi-agent performance and operations.
- [Monitor Microsoft Agent Framework using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/agent-framework.md): OpenLIT auto-instruments Microsoft Agent Framework via OpenTelemetry, tracing agent execution, tool calls, and workflows for AI observability.
- [Monitor AI Agent Governance using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/agent-governance-toolkit.md): OpenLIT integrates with Microsoft's Agent Governance Toolkit for AI observability into policy evaluations, trust scores, and capability violations.
- [Monitor AI21 using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/ai21.md): OpenLIT auto-instruments AI21 models with OpenTelemetry for AI observability, capturing performance, token usage, and cost tracking across your LLM calls.
- [Monitor Claude using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/anthropic.md): OpenLIT auto-instruments Anthropic Claude with OpenTelemetry, enabling AI observability with cost tracking, token usage, and performance tracing for LLM apps.
- [Monitor Assembly AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/assemblyai.md): OpenLIT brings AI observability to AssemblyAI's speech and audio models via OpenTelemetry, tracking performance, cost tracking, and voice input settings.
- [Monitor AstraDB using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/astradb.md): OpenLIT auto-instruments AstraDB as a vector store using OpenTelemetry, providing AI observability with tracing into performance and operation stats.
- [Monitor Azure AI Inference using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/azure-ai-inference.md): OpenLIT auto-instruments Azure AI Inference models through OpenTelemetry, delivering AI observability with cost tracking, token usage, and performance data.
- [Monitor Azure OpenAI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/azure-openai.md): OpenLIT auto-instruments Azure OpenAI models via OpenTelemetry, providing AI observability with cost tracking, token usage, and performance monitoring.
- [Monitor Amazon Bedrock using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/bedrock.md): OpenLIT auto-instruments Amazon Bedrock models using OpenTelemetry, offering AI observability with cost tracking, token usage, and performance tracing.
- [Monitor Browser Use using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/browser-use.md): OpenLIT auto-instruments Browser Use agents through OpenTelemetry, adding AI observability with tracing into browser agent performance and operations.
- [Monitor ChromaDB using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/chromadb.md): OpenLIT auto-instruments ChromaDB as a vector store with OpenTelemetry, giving you AI observability and tracing into query performance and operation stats.
- [Monitor Claude Agent SDK using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/claude-agent-sdk.md): OpenLIT auto-instruments Anthropic's Claude Agent SDK via OpenTelemetry, adding AI observability with tracing across agent runs, tool calls, and LLM calls.
- [Monitor Cohere using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/cohere.md): OpenLIT auto-instruments Cohere models using OpenTelemetry, delivering AI observability with cost tracking and token usage monitoring for LLM apps.
- [Monitor ControlFlow using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/controlflow.md): OpenLIT auto-instruments AI agents built with ControlFlow via OpenTelemetry, adding AI observability and tracing into performance and operation stats.
- [Monitor Crawl4AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/crawl4ai.md): OpenLIT auto-instruments Crawl4AI crawling agents with OpenTelemetry, bringing AI observability and tracing into crawler performance and operation stats.
- [Monitor CrewAI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/crewai.md): OpenLIT auto-instruments AI agents built with CrewAI via OpenTelemetry, providing AI observability and tracing into multi-agent performance and operations.
- [Monitor DeepSeek using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/deepseek.md): OpenLIT auto-instruments DeepSeek models (via the OpenAI SDK) with OpenTelemetry, enabling AI observability with cost tracking and token usage monitoring.
- [Monitor DigitalOcean GenAI (pydo) using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/digitalocean.md): OpenLIT auto-instruments DigitalOcean's GenAI Platform via the pydo SDK, delivering AI observability with cost tracking across chat, embeddings, and agents.
- [Monitor DigitalOcean Gradient using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/digitalocean-gradient.md): OpenLIT auto-instruments DigitalOcean's Gradient AI Platform via the gradient SDK, giving AI observability with cost tracking across chat, image, and RAG calls.
- [Monitor DSPy using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/dspy.md): OpenLIT auto-instruments AI applications built with DSPy using OpenTelemetry, adding AI observability and tracing into pipeline performance and operations.
- [Monitor Dynamiq using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/dynamiq.md): OpenLIT auto-instruments AI agents built with Dynamiq through OpenTelemetry, providing AI observability and tracing into agent performance and operations.
- [Monitor ElevenLabs using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/elevenlabs.md): OpenLIT auto-instruments ElevenLabs' voice and speech models via OpenTelemetry, offering AI observability with cost tracking across voice generation calls.
- [Monitor Featherless using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/featherless.md): OpenLIT auto-instruments Featherless models (via the OpenAI SDK) with OpenTelemetry, enabling AI observability with cost tracking and token usage monitoring.
- [Monitor FireCrawl using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/firecrawl.md): Track FireCrawl web crawling agents with OpenTelemetry auto-instrumentation for AI observability into crawl performance and operation stats.
- [Monitor GitHub Models using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/github-models.md): Monitor GitHub Models LLM apps built on azure-ai-inference with OpenTelemetry auto-instrumentation for AI observability, tokens, and cost.
- [Monitor Google ADK using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/google-adk.md): Monitor AI agents built with Google Agent Development Kit using OpenTelemetry auto-instrumentation for AI observability into execution and tool calls.
- [Monitor Google AI Studio using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/google-ai-studio.md): Track LLM apps built with Google AI Studio's Gemini models via OpenTelemetry auto-instrumentation, covering AI observability, tokens, and cost tracking.
- [Monitor GPT4All using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/gpt4all.md): Add AI observability to LLM apps running local GPT4All models via OpenTelemetry auto-instrumentation, tracking performance and token usage.
- [Monitor Groq using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/groq.md): Gain AI observability into LLM apps powered by Groq's fast inference API with OpenTelemetry auto-instrumentation, tracking tokens and cost.
- [Monitor Guardrails AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/guardrails.md): Apply OpenTelemetry auto-instrumentation for AI evaluation of LLM apps validated with the Guardrails AI library, tracking performance and operation stats.
- [Monitor Haystack using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/haystack.md): Bring OpenTelemetry tracing to Haystack retrieval-augmented pipelines, giving AI observability into component execution and operation stats.
- [Monitor HuggingFace using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/huggingface.md): Instrument Hugging Face Transformers, the Inference API, and Transformers.js with OpenTelemetry for AI observability into tokens, cost, and inference calls.
- [Monitor Julep AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/julep-ai.md): Enable AI observability for agents built with Julep AI through OpenTelemetry auto-instrumentation, tracking performance and operation stats automatically.
- [Monitor Krutrim using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/krutrim.md): Track LLM apps built on OLA Krutrim models, accessed via the OpenAI SDK, using OpenTelemetry auto-instrumentation for AI observability and cost tracking.
- [Monitor LangChain using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/langchain.md): Instrument LangChain apps built on langchain-core with OpenTelemetry auto-instrumentation, delivering AI observability into chains and execution performance.
- [Monitor LangGraph using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/langgraph.md): Trace LangGraph agent workflows and graph execution with OpenTelemetry auto-instrumentation for AI observability into tool usage and state transitions.
- [Monitor Letta using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/letta.md): Monitor AI agents built with Letta using OpenTelemetry auto-instrumentation, capturing AI observability data on performance and operation stats.
- [Monitor LiteLLM using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/litellm.md): Get AI observability into LLM apps routed through LiteLLM's unified gateway via OpenTelemetry auto-instrumentation, tracking performance and operation stats.
- [Monitor LlamaIndex using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/llama-index.md): Add OpenTelemetry auto-instrumentation to LlamaIndex retrieval and query pipelines for AI observability into indexing and query engine stats.
- [Monitor MCP using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/mcp.md): OpenLIT auto-instruments Model Context Protocol (MCP) servers and clients via OpenTelemetry, tracing JSON-RPC calls, tool execution, and session lifecycle.
- [Monitor mem0 using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/mem0.md): Track the mem0 memory layer for LLM apps with OpenTelemetry auto-instrumentation, providing AI observability into memory read/write performance.
- [Monitor Milvus using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/milvus.md): Monitor Milvus vector database operations behind LLM apps using OpenTelemetry auto-instrumentation, gaining AI observability into query performance.
- [Monitor Mistral AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/mistral.md): Track LLM apps built on Mistral AI models with OpenTelemetry auto-instrumentation for AI observability, covering tokens, cost, and performance.
- [Monitor MultiOn using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/multion.md): Monitor autonomous browser agents built with MultiOn using OpenTelemetry auto-instrumentation, delivering AI observability into agent operation stats.
- [Monitor NVIDIA NIM using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/nvidia-nim.md): OpenLIT auto-instruments NVIDIA NIM LLM applications with OpenTelemetry, delivering AI observability into performance, token usage, and cost tracking.
- [Monitor OCI Generative AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/oci.md): OpenLIT brings AI observability to Oracle Cloud Infrastructure Generative AI via OpenTelemetry, tracing OCI SDK and LangChain chat, text, and embedding calls.
- [Monitor Ollama using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/ollama.md): OpenLIT brings AI observability to Ollama LLM apps via OpenTelemetry auto-instrumentation, tracing performance and usage across Python and TypeScript SDKs.
- [Monitor OpenAI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/openai.md): Monitor OpenAI LLM applications with OpenTelemetry auto-instrumentation, giving AI observability into performance, token usage, and cost tracking.
- [Monitor OpenAI Agents](https://docs.openlit.io/latest/sdk/integrations/openai-agents.md): Trace AI agents built on the OpenAI Agents SDK with OpenTelemetry auto-instrumentation for AI observability into agent performance and operation stats.
- [Monitor AI Applications using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/overview.md): Track LLM Costs, Agent actions, Tokens, Performance along with User Interactions
- [Monitor Phidata using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/phidata.md): OpenLIT adds AI observability to Phidata AI agents via OpenTelemetry auto-instrumentation, tracing agent performance and operation stats automatically.
- [Monitor Pinecone using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/pinecone.md): Trace Pinecone vector store calls in RAG applications with OpenTelemetry auto-instrumentation for AI observability into query performance and operation stats.
- [Monitor Prem AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/premai.md): Monitor Prem AI LLM applications with OpenTelemetry auto-instrumentation, enabling AI observability into performance, token usage, and cost tracking.
- [Monitor Pydantic AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/pydantic.md): Trace Pydantic AI agents with OpenTelemetry auto-instrumentation for AI observability into agent performance and operation stats, with zero code changes.
- [Monitor Qdrant using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/qdrant.md): OpenLIT auto-instruments Qdrant vector database operations with OpenTelemetry, delivering AI observability into query performance and operation stats.
- [Monitor Reka using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/reka.md): Monitor Reka AI LLM applications through OpenTelemetry auto-instrumentation, gaining AI observability into performance, token usage, and cost tracking.
- [Monitor Replicate using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/replicate.md): Trace AI applications built on the Replicate API with OpenTelemetry auto-instrumentation, delivering AI observability into model usage and performance.
- [Monitor Sarvam AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/sarvam.md): OpenLIT brings AI observability to Sarvam AI LLM applications via OpenTelemetry auto-instrumentation, tracking performance, token usage, and cost tracking.
- [Monitor smolagents using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/smolagents.md): OpenLIT auto-instruments Hugging Face smolagents via OpenTelemetry, tracing agent runs, planning steps, and tool calls for AI observability.
- [Monitor Strands Agents using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/strands.md): Trace Strands Agents SDK applications with OpenTelemetry auto-instrumentation for AI observability into agent invocations, tool calls, and chat completions.
- [Monitor SwarmZero using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/swarmzero.md): Monitor SwarmZero AI agents using OpenTelemetry auto-instrumentation, gaining AI observability into agent performance and operation stats automatically.
- [Monitor Titan ML using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/titan-ml.md): OpenLIT auto-instruments Titan ML inference with OpenTelemetry for AI observability, tracing performance, token usage, and cost tracking with zero setup.
- [Monitor Together AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/together.md): Monitor Together AI LLM applications with OpenTelemetry auto-instrumentation, gaining AI observability into performance, token usage, and cost tracking.
- [Monitor Vercel AI SDK using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/vercel-ai.md): Trace AI applications built with the Vercel AI SDK using OpenTelemetry auto-instrumentation for AI observability into performance and token usage.
- [Monitor Vertex AI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/vertexai.md): OpenLIT auto-instruments Google Vertex AI LLM applications with OpenTelemetry, providing AI observability into performance, token usage, and cost tracking.
- [Monitor vLLM using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/vllm.md): Monitor vLLM inference server applications with OpenTelemetry auto-instrumentation, gaining AI observability into performance and token usage tracking.
- [Monitor xAI using OpenTelemetry](https://docs.openlit.io/latest/sdk/integrations/xai.md): Trace xAI Grok LLM applications with OpenTelemetry auto-instrumentation for AI observability into performance, token usage, and cost tracking.
- [Overview](https://docs.openlit.io/latest/sdk/overview.md): Production-ready AI observability with zero code changes. Monitor LLM applications, track token usage, detect hallucinations, and optimize costs with OpenTelemetry-native instrumentation.
- [Get started with AI Observability](https://docs.openlit.io/latest/sdk/quickstart-ai-observability.md): Start monitoring your AI applications with the OpenLIT SDK in a few steps
- [GPU Performance Monitoring](https://docs.openlit.io/latest/sdk/quickstart-gpu.md): Simple GPU monitoring setup for AI workloads. Track NVIDIA and AMD GPU usage, temperature, and costs with zero code changes using OpenTelemetry.
- [Secure your AI app against risks](https://docs.openlit.io/latest/sdk/quickstart-guard.md): Quickly secure your app from Prompt Injection, Sensitive Topics, and Topic Restriction
- [Get started with MCP Monitoring](https://docs.openlit.io/latest/sdk/quickstart-mcp-observability.md): Quickly start monitoring your MCP (Model Context Protocol) Applications in just a single line of code
- [Evaluate LLMs and AI Agents](https://docs.openlit.io/latest/sdk/quickstart-programmatic-evals.md): Quickly evaluate your model responses for Hallucination, Bias, and Toxicity
- [Get started with VectorDB Observability](https://docs.openlit.io/latest/sdk/quickstart-vectordb-observability.md): Quickly start monitoring your Vector Database Applications in just a single line of code

## OpenAPI Specs

- [rule-engine](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/rule-engine/rule-engine.yml)
- [public-pricing](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/manage-models/public-pricing.yml)
- [providers](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/manage-models/providers.yml)
- [models](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/manage-models/models.yml)
- [import](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/manage-models/import.yml)
- [export](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/manage-models/export.yml)
- [vault](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/vault/vault.yml)
- [prompt-hub](https://docs.openlit.io/latest/openlit/developer-resources/api-reference/endpoint/prompt-hub/prompt-hub.yml)
- [openiapi](https://docs.openlit.io/latest/api-reference/openiapi.yml)
- [openapi](https://docs.openlit.io/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/openlit/openlit)
- [Community](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ)
- [Blog](https://openlit.io/blogs)