# langfuse/langfuse

🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Repository: https://github.com/langfuse/langfuse
Canonical: https://ross.abutalabs.com/products/langfuse
Homepage: https://langfuse.com
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: analytics, llm, llmops, large-language-models, openai, self-hosted, ycombinator, monitoring, observability, open-source, langchain, llama-index, evaluation, prompt-engineering, prompt-management, playground, llm-evaluation, llm-observability, autogen
Last push: 2026-08-26T22:10:00+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 85
- inputs: {"age_days": 1203, "days_push": 7, "days_rel": 6, "gap_med": 0.0, "n_releases_24m": 411}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 33767, forks 3650 (observed 2026-08-28T04:11:58.427266+00:00)

## What it is
Langfuse is an open-source AI engineering platform for LLM observability, tracing, evaluation, prompt management, and metrics, deployable as a cloud service or self-hosted. It integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and 100+ frameworks via Python/JS SDKs to trace, evaluate, and improve AI agent applications.

## Use cases
- trace and debug LLM calls and agent steps in production
- evaluate LLM app output quality with LLM-as-judge and human review
- manage and version prompts separately from code
- monitor LLM cost, latency, and quality with dashboards and alerts
- run experiments comparing prompts and models on test datasets
- self-host an LLM observability platform
- collect user feedback and human annotations on traces

## When to choose
- you need production observability and tracing for LLM or agent applications
- you want integrated prompt management, evals, and metrics in one platform
- you need OpenTelemetry-based tracing with broad framework integrations
- you want a self-hostable alternative to closed LLM monitoring tools

## When to avoid
- you only need simple application logging without LLM-specific features
- you need a lightweight library-only solution with no server component
- you require a fully permissive license for commercial redistribution without checking terms

## Facets
- artifact type: service
- maturity: active
- function: monitoring, tracing, analytics, prompt-engineering, llm-inference, alerting, data-visualization, developer-tools
- domain: large-language-models, monitoring, analytics, developer-tools, self-hosted
- platform: self-hosted, cloud, python
- tags: llm-observability, llm-evaluation, prompt-management, llmops, opentelemetry, agent-evals, llm-as-judge, tracing, playground, human-annotation, ai-agents, docker, web-server, nodejs, typescript

## Member repositories
- langfuse/langfuse (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:58.427266+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 2026-08-29T16:28:09.054850+00:00, confidence not recorded.
  - readme: https://github.com/langfuse/langfuse (fetched 2026-08-28T04:11:58.427266+00:00, sha de11dc52ce49)
  - homepage: https://langfuse.com (fetched 2026-08-29T07:48:52.487846+00:00, sha 58ad793e94d6)
  - site_page: https://langfuse.com/docs/v4 (fetched 2026-08-29T07:48:52.491206+00:00, sha 3e3d4b54b871)
  - site_page: https://langfuse.com/docs (fetched 2026-08-29T07:48:52.493579+00:00, sha e4cf23b96428)
  - site_page: https://langfuse.com/docs/observability/overview (fetched 2026-08-29T07:48:52.495879+00:00, sha f41bf4c184cc)
  - site_page: https://langfuse.com/docs/prompt-management/overview (fetched 2026-08-29T07:48:52.498255+00:00, sha 88bf0fdf3b25)
  - site_page: https://langfuse.com/docs/evaluation/overview (fetched 2026-08-29T07:48:52.500179+00:00, sha 3e6e46d7a98c)
  - site_page: https://langfuse.com/docs/metrics/overview (fetched 2026-08-29T07:48:52.501882+00:00, sha 91baff97fd23)
  - site_page: https://langfuse.com/docs/get-started (fetched 2026-08-29T07:48:52.503645+00:00, sha 77631a725a95)
  - site_page: https://langfuse.com/changelog (fetched 2026-08-29T07:48:52.505990+00:00, sha 7f38c1eafd38)
- Data as of 2026-08-30T08:39:29.467469+00:00.