OSS Tanbou
View on GitHubProject website

Langfuse — unify tracing, evaluation, and prompt management for LLM applications

OSS scale score 289.8OSS health 93Update pace 738 commits/30d
About these scores

OSS scale score is an unbounded metric that log-compresses and weights Stars, Watchers, Forks, and Contributors. Discovery score is the current OSS scale score minus the score at discovery. Update pace is commits in the last 30 days, growth momentum is the OSS scale score difference within the recent observation window, and OSS health is a 0–100 rating based on available recency, Community Health, and release data.

Stars
34,834
Primary language
TypeScript
License
Not determined
Repository last updated
Sep 19, 2026

Overview

Langfuse is an LLM engineering platform combining tracing, prompt versioning, evaluations, datasets, and playground workflows, with both managed cloud and self-hosted deployment plus broad model/framework integrations.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Trace LLM calls, retrieval, and agent actions

SDK and framework integrations capture traces spanning model calls, retrieval, agent steps, and user sessions for debugging.

Sources: [2][3]

Integrate prompts, evaluations, datasets, and playground workflows

Prompt versioning, LLM-as-a-judge, code evaluators, human labels, dataset runs, and playground iteration share one platform.

Sources: [2][3]

For teams that want production traces to feed continuous LLM quality improvement

It suits workflows that turn observed failures into prompt changes, datasets, and repeatable evaluations.

Sources: [2]

Separate MIT core from Enterprise-licensed directories

The core is MIT, but ee/ and related enterprise directories use a separate Enterprise License. Self-hosting does not imply every feature is MIT-licensed.

Sources: [4][5]

Official sources

  1. [1]langfuse/langfuse repository(2026-09-20)
  2. [2]Langfuse README(2026-09-20)
  3. [3]Langfuse self-hosting documentation(2026-09-20)
  4. [4]Langfuse root mixed-license notice(2026-09-20)
  5. [5]Langfuse Enterprise License(2026-09-20)
Supplemental curator note

Langfuse connects development, evaluation, and production monitoring for LLM applications on one platform. The core is MIT-licensed, while `ee/`, `web/src/ee/`, and `worker/src/ee/` are governed by the Enterprise License. Do not treat the entire repository as a single MIT work; verify whether required self-hosted features are core or enterprise.

Try it in 3 steps

  1. 1

    Get the source

    git clone --depth 1 https://github.com/langfuse/langfuse.git
  2. 2

    Enter the repository

    cd langfuse
  3. 3

    Check the official steps

    Continue with the commands in the README Installation, Quick Start, or Getting Started section.

    find . -maxdepth 1 -iname 'README*' -exec sed -n '1,220p' {} \; -quit
Check the official README

Growth

Growth trends · Last 30 days

34,834 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
738
Open PRs
628

Development activity is still being collected.

Built with

Categories and tags

Categories

Tags

GitHub data

GitHub dataView detailed GitHub data
View on GitHub

GitHub Topics

  • analytics
  • llm
  • llmops
  • large-language-models
  • openai
  • self-hosted
  • ycombinator
  • monitoring
  • observability
  • open-source
  • langchain
  • llama-index
Stars
34,834
Forks
3,816
Watchers
113
Open issues
301
Contributors
205
Primary language
TypeScript
License
Not determined
Repository last updated
Sep 19, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.