# openlit/openlit

Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers, VectorDBs, Agent Frameworks and GPUs.

Repository: https://github.com/openlit/openlit
Canonical: https://ross.abutalabs.com/products/openlit
Homepage: https://docs.openlit.io
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: observability, llmops, ai-observability, openai, metrics, clickhouse, genai, grafana, langchain, llms, monitoring-tool, opentelemetry, otlp, python, tracing, distributed-tracing, open-source, gpu-monitoring, amd-gpu, nvidia-smi
Last push: 2026-08-26T22:09:59+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 68
- inputs: {"age_days": 953, "days_push": 7, "days_rel": 8, "gap_med": 0.0, "n_releases_24m": 237}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2718, forks 363 (observed 2026-08-28T04:07:12.133616+00:00)

## What it is
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
- artifact type: service
- maturity: active
- function: monitoring, tracing, llm-inference, agent-framework, prompt-engineering, sdk, self-hosted
- domain: large-language-models, monitoring, developer-tools
- platform: self-hosted, python, go
- tags: llm-observability, opentelemetry, llmops, gpu-monitoring, guardrails, evaluations, prompt-management, cost-tracking, clickhouse, genai, ai-agents, devops, docker, kubernetes, nodejs, web-server

## Member repositories
- openlit/openlit (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:12.133616+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:15:19.637359+00:00, confidence not recorded.
  - readme: https://github.com/openlit/openlit (fetched 2026-08-28T04:07:12.133616+00:00, sha 4ff45d98b079)
  - homepage: https://docs.openlit.io (fetched 2026-08-29T09:58:43.656871+00:00, sha c67fd08fb216)
  - site_page: https://docs.openlit.io/latest/openlit/installation (fetched 2026-08-29T09:58:43.666395+00:00, sha e7d97e7efbcb)
  - registry_npm: https://registry.npmjs.org/openlit (fetched 2026-08-29T09:58:43.671133+00:00, sha 37bd13b0349a)
- Data as of 2026-08-30T08:39:29.467469+00:00.