openlit/openlit

Health v2 · maintenance only

Adoption not part of the score

2792 stars · 400 forks observed · 2026-09-24

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

OpenLIT is an open-source AI engineering platform providing OpenTelemetry-native LLM observability, evaluations, guardrails, prompt management, vault, and playground, with SDKs for Python, TypeScript, and Go. It is fully self-hostable via Docker or Kubernetes using a lightweight three-component stack (OpenLIT, ClickHouse, OpenTelemetry Collector) and integrates with 50+ LLM providers, vector databases, agent frameworks, and GPUs.

Use cases

• trace llm calls in production
• monitor gpu utilization for ai workloads
• track llm token costs and latency
• version and deploy prompts without code changes
• evaluate llm outputs automatically
• add guardrails to ai agents
• self-host llm observability stack
• instrument langchain or crewai agents with opentelemetry

When to choose

• you need vendor-neutral OpenTelemetry-native LLM tracing and metrics
• you want a fully self-hostable observability platform for GenAI apps
• you need combined LLM, vector DB, and GPU monitoring in one dashboard
• you want prompt versioning, evaluations, and guardrails alongside observability

When to avoid

• you only need simple application logging without LLM-specific telemetry
• you prefer a fully managed SaaS with no self-hosting components
• your stack does not use LLMs or generative AI

Facets

service · maturity active

monitoring tracing llm-inference agent-framework prompt-engineering sdk self-hosted large-language-models monitoring developer-tools self-hosted python go llm-observability opentelemetry llmops gpu-monitoring guardrails evaluations prompt-management cost-tracking clickhouse genai ai-agents devops docker kubernetes nodejs web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="openlit/openlit")