Langfuse

What's Changed

Feat

• feat(preview): pin the preview URL to the top of the PR description by @nmtrang29 in https://github.com/langfuse/langfuse/pull/15588
• feat(experiments): enhance MultiStepExperimentForm with review step validation and error messaging by @marliessophie in https://github.com/langfuse/langfuse/pull/15560
• feat(agent): Extract & extend background execution for in-app-agent (LFE-14373) by @LysanderKie in https://github.com/langfuse/langfuse/pull/15594
• feat(preview): add a top strip linking previews back to their PR by @nmtrang29 in https://github.com/langfuse/langfuse/pull/15580
• feat(v4): show deprecated API last seen time by @maxdeichmann in https://github.com/langfuse/langfuse/pull/15609
• feat(migration-v4): auto-generate API keys on prompt copy by @marliessophie in https://github.com/langfuse/langfuse/pull/15604

Fixes

• fix(assistant): Perform side effects after tool calls by @bezbac in https://github.com/langfuse/langfuse/pull/15587
• fix(api): derive dashboard widget minVersion from the deployment write mode by @LysanderKie in https://github.com/langfuse/langfuse/pull/15565
• fix(v4-migration): hide ready project hints by @maxdeichmann in https://github.com/langfuse/langfuse/pull/15601
• fix(v4-migration): navigate assistant flow to evals by @maxdeichmann in https://github.com/langfuse/langfuse/pull/15600
• fix(v4-migration): treat projects without data as migrated by @maxdeichmann in https://github.com/langfuse/langfuse/pull/15603
• fix(web): validate unsupported evaluator JSONPath by @wochinge in https://github.com/langfuse/langfuse/pull/15592
• fix(evals): preserve configured model while options load by @marliessophie in https://github.com/langfuse/langfuse/pull/15583
• fix(evals): target logical root observations by @sumerman in https://github.com/langfuse/langfuse/pull/15569
• fix: optimize ClickHouse score filtering without dropping score data by @sumerman in https://github.com/langfuse/langfuse/pull/15591
• fix(web): cap non-streaming LLM requests by @wochinge in https://github.com/langfuse/langfuse/pull/15613
• fix(experiments): return stable experiment id upon POST /dataset-run-items to perserve SDK expectations by @marliessophie in https://github.com/langfuse/langfuse/pull/15616
• fix(evals): restore 7-day evaluator costs by @wochinge in https://github.com/langfuse/langfuse/pull/15614
• fix(evals): encode Bedrock inference profile ARN routes by @hassiebp in https://github.com/langfuse/langfuse/pull/15619

Refactor

• refactor(v4-migration): rename migration badge component and update logic by @marliessophie in https://github.com/langfuse/langfuse/pull/15593

Chore

• chore: remove sfdc-backfill directory from gitignore by @Steffen911 in https://github.com/langfuse/langfuse/pull/15605
• chore(release): flip Docker latest markers to the v4 line by @Steffen911 in https://github.com/langfuse/langfuse/pull/15607
• chore(deps): upgrade to typescript 7 native compiler with ts6 api wrapper by @wochinge in https://github.com/langfuse/langfuse/pull/14921

Full Changelog: https://github.com/langfuse/langfuse/compare/v4.0.0...v4.1.0

<img width="2400" alt="hero-b (1)" src="https://github.com/user-attachments/assets/5810ae13-15d6-4b60-afd2-927adc501861" />

<div align="center">

<div>

<h3>

<a href="https://cloud.langfuse.com">

<strong>Langfuse Cloud</strong>

</a> ·

<a href="https://langfuse.com/docs/deployment/self-host">

<strong>Self Host</strong>

</a> ·

<a href="https://langfuse.com/demo">

<strong>Demo</strong>

</a>

</h3>

</div>

<div>

<a href="https://langfuse.com/docs"><strong>Docs</strong></a> ·

<a href="https://langfuse.com/issues"><strong>Report Bug</strong></a> ·

<a href="https://langfuse.com/ideas"><strong>Feature Request</strong></a> ·

<a href="https://langfuse.com/changelog"><strong>Changelog</strong></a> ·

<a href="https://langfuse.com/roadmap"><strong>Roadmap</strong></a> ·

</div>

<br/>

<div>

</div>

</div>

<p align="center">

<a href="https://github.com/langfuse/langfuse/blob/main/LICENSE">

<img src="https://img.shields.io/badge/License-MIT-E11311.svg" alt="MIT License">

</a>

<a href="https://www.ycombinator.com/companies/langfuse"><img src="https://img.shields.io/badge/Y%20Combinator-W23-orange" alt="Y Combinator W23"></a>

<a href="https://hub.docker.com/u/langfuse" target="_blank">

<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langfuse/langfuse?labelColor=%20%23FDB062&logo=Docker&labelColor=%20%23528bff"></a>

<a href="https://pypi.python.org/pypi/langfuse"><img src="https://img.shields.io/pypi/dm/langfuse?logo=python&logoColor=white&label=pypi%20langfuse&color=blue" alt="langfuse Python package on PyPi"></a>

<a href="https://www.npmjs.com/package/langfuse"><img src="https://img.shields.io/npm/dm/langfuse?logo=npm&logoColor=white&label=npm%20langfuse&color=blue" alt="langfuse npm package"></a>

<br/>

<a href="https://discord.com/invite/7NXusRtqYU" target="_blank">

<img src="https://img.shields.io/discord/1111061815649124414?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"

alt="chat on Discord"></a>

<a href="https://twitter.com/intent/follow?screen_name=langfuse" target="_blank">

<img src="https://img.shields.io/twitter/follow/langfuse?logo=X&color=%20%23f5f5f5"

alt="follow on X(Twitter)"></a>

<a href="https://www.linkedin.com/company/langfuse/" target="_blank">

<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"

alt="follow on LinkedIn"></a>

<a href="https://github.com/langfuse/langfuse/graphs/commit-activity" target="_blank">

<img alt="Commits last month" src="https://img.shields.io/github/commit-activity/m/langfuse/langfuse?labelColor=%20%2332b583&color=%20%2312b76a"></a>

<a href="https://github.com/langfuse/langfuse/" target="_blank">

<img alt="Issues closed" src="https://img.shields.io/github/issues-search?query=repo%3Alangfuse%2Flangfuse%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>

<a href="https://github.com/langfuse/langfuse/discussions/" target="_blank">

<img alt="Discussion posts" src="https://img.shields.io/github/discussions/langfuse/langfuse?labelColor=%20%239b8afb&color=%20%237a5af8"></a>

</p>

<p align="center">

<a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>

<a href="./README.cn.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>

<a href="./README.ja.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>

<a href="./README.kr.md"><img alt="README in Korean" src="https://img.shields.io/badge/한국어-d9d9d9"></a>

</p>

Langfuse is an open source LLM engineering platform. It helps teams collaboratively

develop, monitor, evaluate, and debug AI applications. Langfuse can be self-hosted in minutes and is battle-tested. Proudly made with ClickHouse open source database.

### 🧑‍💻 We're hiring

Langfuse is growing fast (we doubled the team in the last 6 months) - since January 2026 we're part of ClickHouse, we're hiring engineering hybrid across the EU.

We hire engineers who love open source and great developer experiences.

See open roles →

✨ Core Features

<img width="2400" alt="features" src="https://github.com/user-attachments/assets/0fad3dee-f3ad-423c-9f0d-7ccd0f26cc2d" />

• LLM Application Observability: Instrument your app and start ingesting traces to Langfuse, thereby tracking LLM calls and other relevant logic in your app such as retrieval, embedding, or agent actions. Inspect and debug complex logs and user sessions. Try the interactive demo to see this in action.

• Prompt Management helps you centrally manage, version control, and collaboratively iterate on your prompts. Thanks to strong caching on server and client side, you can iterate on prompts without adding latency to your application.

• Evaluations are key to the LLM application development workflow, and Langfuse adapts to your needs. It supports LLM-as-a-judge, Code evaluators, user feedback collection, manual labeling, and custom evaluation pipelines via APIs/SDKs.

• Datasets enable test sets and benchmarks for evaluating your LLM application. They support continuous improvement, pre-deployment testing, structured experiments, flexible evaluation, and seamless integration with frameworks like LangChain and LlamaIndex.

• LLM Playground is a tool for testing and iterating on your prompts and model configurations, shortening the feedback loop and accelerating development. When you see a bad result in tracing, you can directly jump to the playground to iterate on it.

• Comprehensive API: Langfuse is frequently used to power bespoke LLMOps workflows while using the building blocks provided by Langfuse via the API. OpenAPI spec, Postman collection, and typed SDKs for Python, JS/TS are available.

📦 Deploy Langfuse

<img width="2400" alt="deploy" src="https://github.com/user-attachments/assets/cf72e7f8-db7f-4e11-a2a1-ecfbe46f262c" />

Langfuse Cloud

Managed deployment by the Langfuse team, generous free-tier, no credit card required.

<div align="center">

<a href="https://cloud.langfuse.com" target="_blank">

<img alt="Static Badge" src="https://img.shields.io/badge/»%20Sign%20up%20for%20Langfuse%20Cloud-8A2BE2?&color=black">

</a>

</div>

Self-Host Langfuse

Run Langfuse on your own infrastructure:

• Local (docker compose): Run Langfuse on your own machine in 5 minutes using Docker Compose.

  # Get a copy of the latest Langfuse repository
  git clone --depth=1 https://github.com/langfuse/langfuse.git
  cd langfuse

  # Run the langfuse docker compose
  docker compose up

• VM: Run Langfuse on a single Virtual Machine using Docker Compose.
• Kubernetes (Helm): Run Langfuse on a Kubernetes cluster using Helm. This is the preferred production deployment.
• Terraform Templates: AWS, Azure, GCP

See self-hosting documentation to learn more about architecture and configuration options.

[!TIP]

Self-hosting Langfuse? Subscribe to the self-hosting update list to get an email about important features and new releases for open source Langfuse — self-hosting updates only, no marketing.

🔌 Integrations

<img width="2400" alt="integrations" src="https://github.com/user-attachments/assets/b85c9a45-68f0-4f76-b545-0e8632abef9f" />

Main Integrations:

| Integration | Supports | Description |

| ---------------------------------------------------------------------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |

| SDK | Python, JS/TS | Manual instrumentation using the SDKs for full flexibility. |

| OpenAI | Python, JS/TS | Automated instrumentation using drop-in replacement of OpenAI SDK. |

| Langchain | Python, JS/TS | Automated instrumentation by passing callback handler to Langchain application. |

| LlamaIndex | Python | Automated instrumentation via LlamaIndex callback system. |

| Haystack | Python | Automated instrumentation via Haystack content tracing system. |

| LiteLLM | Python, JS/TS (proxy only) | Use any LLM as a drop in replacement for GPT. Use Azure, OpenAI, Cohere, Anthropic, Ollama, VLLM, Sagemaker, HuggingFace, Replicate (100+ LLMs). |

| Vercel AI SDK | JS/TS | TypeScript toolkit designed to help developers build AI-powered applications with React, Next.js, Vue, Svelte, Node.js. |

| Mastra | JS/TS | Open source framework for building AI agents and multi-agent systems. |

| API | | Directly call the public API. OpenAPI spec available. |

Packages integrated with Langfuse:

| Name | Type | Description |

| ----------------------------------------------------------------------- | ------------------ | ----------------------------------------------------------------------------------------------------------------------- |

| Instructor | Library | Library to get structured LLM outputs (JSON, Pydantic) |

| DSPy | Library | Framework that systematically optimizes language model prompts and weights |

| Mirascope | Library | Python toolkit for building LLM applications. |

| Ollama | Model (local) | Easily run open source LLMs on your own machine. |

| Amazon Bedrock | Model | Run foundation and fine-tuned models on AWS. |

| AutoGen | Agent Framework | Open source LLM platform for building distributed agents. |

| Flowise | Chat/Agent&nbsp;UI | JS/TS no-code builder for customized LLM flows. |

| Langflow | Chat/Agent&nbsp;UI | Python-based UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows. |

| Dify | Chat/Agent&nbsp;UI | Open source LLM app development platform with no-code builder. |

| OpenWebUI | Chat/Agent&nbsp;UI | Self-hosted LLM Chat web ui supporting various LLM runners including self-hosted and local models. |

| Promptfoo | Tool | Open source LLM testing platform.