https://github.com/langfuse/langfuse
🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
https://github.com/langfuse/langfuse
ai-gateway analytics evaluation gateway langchain large-language-models llama-index llm llm-evaluation llm-gateway llm-observability llmops monitoring observability open-source openai playground prompt-engineering prompt-management self-hosted
Last synced: 1 day ago
JSON representation
🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or use Langfuse Cloud.
- Host: GitHub
- URL: https://github.com/langfuse/langfuse
- Owner: langfuse
- License: other
- Created: 2023-05-18T17:47:09.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2026-11-11T20:16:59.000Z (5 days ago)
- Last Synced: 2026-11-11T20:17:56.226Z (5 days ago)
- Topics: ai-gateway, analytics, evaluation, gateway, langchain, large-language-models, llama-index, llm, llm-evaluation, llm-gateway, llm-observability, llmops, monitoring, observability, open-source, openai, playground, prompt-engineering, prompt-management, self-hosted
- Language: TypeScript
- Homepage: https://langfuse.com
- Size: 262 MB
- Stars: 37,313
- Watchers: 111
- Forks: 4,200
- Open Issues: 1,176
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Codeowners: .github/CODEOWNERS
- Security: SECURITY.md
- Agents: AGENTS.md
Awesome Lists containing this project
- Awesome-LLM-Productization - Langfuse - Open source observability and analytics for LLM applications (Models and Tools / LLM Deployment)
- Awesome-RAG-Production - Langfuse
- awesome-ai-agents-2026 - Langfuse - オープンソース LLM エンジニアリングプラットフォーム: オブザーバビリティ + 評価 + プロンプト管理。 (📊 エージェント評価とオブザーバビリティ / 自動運転)
- awesome-ai-sdks - GitHub
- awesome-llmops - Langfuse - square) | (LLMOps / Observability)
- awesome-ai - langfuse - Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. (LLM Engineering Platform)
- awesome-llm-services - LangFuse
- awesome-production-machine-learning - Langfuse - Langfuse is an observability & analytics solution for LLM-based applications. (Evaluation and Monitoring)
- Awesome-LLM - Langfuse - Open Source LLM Engineering Platform 🪢 Tracing, Evaluations, Prompt Management, Evaluations and Playground. (LLM Applications)
- awesome-open-weight-models - Langfuse - source, self-hostable | (Evaluation Tools / Datasets)
- awesome-mistral - Langfuse - source LLM observability. (Tooling & Dev Experience / Development Tools)
- awesome-agentic-engineering-resources - **Langfuse** - source LLM observability. (🏗️ Reference Implementations & Case Studies / T14 · Observability)
- awesome-ai - Langfuse
- awesome-agent-loop-papers - langfuse - native | (Real-world artifacts / Memory, context, and execution infrastructure)
- awesome-ai-agents - GitHub
- awesome-harness-engineering - Langfuse - hostable LLM observability platform: traces every agent step, manages prompt versions, and runs evals in one tool. Preferred over cloud-only alternatives when data residency or cost control is a constraint.  (Design Primitives / Observability & Tracing)
- awesome-typescript - langfuse/langfuse - 🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform. (Machine Learning and AI / LLM and Inference)
- Awesome-LLM-RAG-Application - langfuse
- awesome-agents - Langfuse - Open-source LLM engineering platform with tracing, evaluations, prompt management, and metrics. (Monitoring and Observability)
- awesome-safety-critical-ai - `langfuse/langfuse`
- Awesome-RAG - LangFuse - Open-source tool for tracking LLM metrics, observability, and prompt management. (📊 Metrics & Evaluation / Response Evaluation Metrics)
- awesome-local-llm - langfuse - an open-source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more (Tools / Testing, Evaluation and Observability)
- AwesomeResponsibleAI - Langfuse
- awesome_ai_agents - Langfuse - 🪢 Open source LLM engineering platform - LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with Llama… (Building / Prompt Engineering)
- AiTreasureBox - langfuse/langfuse - 11-03_17843_0](https://img.shields.io/github/stars/langfuse/langfuse.svg)|🪢 Open source LLM engineering platform. Observability, metrics, evals, prompt management, testing, prompt playground, datasets, LLM evaluations -- 🍊YC W23 🤖 integrate via Typescript, Python / Decorators, OpenAI, Langchain, LlamaIndex, Litellm, Instructor, Mistral, Perplexity, Claude, Gemini, Vertex| (Repos)
- awesome-side-quests - langfuse/langfuse - source LLM observability platform — tracing, evals, prompt management, and a playground in one place (AI & LLM / LLM Apps & Interfaces)
- awesome-llm - langfuse/langfuse - 🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform. (AI Agents / Evaluation and Benchmarks)
- Awesome-AI-Evaluation-Guide - Langfuse - Open-source LLM engineering platform with tracing and prompt management (Tools & Platforms / Open Source Frameworks)
- awesome-prompts - Langfuse -  (Frameworks / Eval & Observability)
- Awesome-AI-Evaluations-Tools - Langfuse - commit/langfuse/langfuse) | (Platforms And Software / Out Of Scope)
- awesome-github-projects - langfuse - 🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform. ⭐35,676 `TypeScript` 🔥 (🤖 AI & Machine Learning)
- awesome-open-data-centric-ai - langfuse
- awesome-evals - Langfuse - judge, feedback, manual labeling), datasets/experiments, prompt mgmt; self-hostable. 🆕 (5 · Evaluation infrastructure (the eval stack: datasets, scorers, online/offline, tracing, CI) / 5f · Observability + eval platforms (tracing · datasets · online/offline · CI))
- awesome-claude-multi-agent - Langfuse - Open-source platform tracing nested multi-agent sessions with evaluation, datasets, and prompt management. (Observability and Debugging)
- awesome - 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 (TypeScript)
- awesome-ai-agents - langfuse/langfuse - Langfuse is an open source LLM engineering platform that enables collaborative development, monitoring, evaluation, and debugging of AI applications with comprehensive observability, prompt management, and integration features. (Agent Integration & Deployment Tools / LLM Framework Tools)
- awesome-harness-engineering - langfuse/langfuse
- awesome-german-open-source-ml - Langfuse - based open-source LLM engineering platform (26.5k+ GitHub stars). Provides LLM observability, tracing, prompt management, evaluations and analytics for building production-grade AI applications. Fully self-hostable under MIT license. Used by enterprises including Merck, Canva and Twilio, processing billions of observations monthly. **Note: Acquired by ClickHouse (Jan 2026). Open-source commitment and MIT license reaffirmed post-acquisition. Team remains Berlin-based.** | <!-- ACCOUNT:langfuse -->🟢<!-- /ACCOUNT --> | <a href="https://github.com/langfuse/langfuse"><img src="res/github_logo.png" width="30" height="30"/></a> <a href="https://langfuse.com/"><img src="res/internet-54.png" width="30" height="30"/></a> (Categories / 🛠️ MLOps)
- awesome-private-ai - Langfuse - Self-hostable LLM observability, tracing, prompt management, and evaluation. (Observability & Evaluation)
- awesome-ccamel - langfuse/langfuse - 🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform. (TypeScript)
- awesome-infra-for-ai - langfuse/langfuse - Langfuse is an open-source LLM engineering platform for developing, monitoring, evaluating, and debugging AI applications, offering observability, prompt management, and evaluation capabilities. (LLMOps / LLM Observability & Tracing)
- awesome-ChatGPT-repositories - langfuse - 🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 (Prompts)
- awesome-ai-agent-stack - langfuse/langfuse - Open-source LLM observability: traces, evals, prompt management; self-hostable. (Evaluation, Observability & Code Review)
- awesome-ai-agents-2026 - Langfuse - OSS LLM observability. Traces, evals, prompts. (🔍 Observability and Evaluation / Tracing and Monitoring)
- awesome-ai-agents-2026 - Langfuse - hostable | Privacy-first, LangChain/CrewAI teams | (7. Agent Observability / Memory Taxonomy)
- awesome-hacking-lists - langfuse/langfuse - 🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 (TypeScript)
- awesome-ai-eval - **Langfuse** - Open-source LLM engineering platform providing tracing, eval dashboards, and prompt analytics. (Platforms / Open Source Platforms)
- github-ultimate-repos - langfuse/langfuse - | ⭐ 36,417★ | 🍴 4,069 | 💻 `TypeScript`🔗 <https://github.com/langfuse/langfuse>📝 🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.⚙️ `Goal decomposition DAG -> dynamic tool routing (MCP JSON-RPC) -> state graph & shared memory scratchpad -> multi-agent execution swarm -> critic-refiner consensus loop.` (📜 Master Categorized Repository Directory (100% Clickable Links) / [03] MULTI-AGENT SYSTEMS, AUTONOMOUS SWARMS, AI ORCHESTRATION & MCP TOOLS)
- awesome-agent-infra - Langfuse GitHub - hostable observability platform. | (Observability and Evaluation / Sandbox Security Papers and Measurement)
- awesome-llm-tools - Langfuse - source LLM observability with prompt management, tracing, evals | Monitoring | (3. Prompt Optimization / Rust)
- Awesome-LLMOps - Langfuse - commit/langfuse/langfuse?color=green) (Orchestration / Application Framework)
- awesome-mcp-servers - Langfuse Prompt Management - Open-source tool for collaborative editing, versioning, evaluating, and releasing prompts, enabling AI teams to manage prompt lifecycles. ([Read more](/details/langfuse-prompt-management.md)) `Open Source` `Prompt Management` `Collaboration` (Ai Integration Mcp Servers)
- jimsghstars - langfuse/langfuse - 🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 (TypeScript)
- awesome-ai-agents - LangFuse - Open-source LLM engineering platform. (Production & Deployment / Monitoring & Observability)
- awesome-selfhosted-ai - Langfuse - LLM engineering platform for tracing, prompt management and evals, self-hostable with Docker. (MIT core, ee/ directories under their own license) (Source-Available)
- llmops - Langfuse - source LLM engineering platform |  | (Orchestration / Application Frameworks)
- Awesome-Prompt-Engineering - GitHub
- awesome-agent-cortex - LangFuse - Open-source LLM engineering platform for tracing and evaluation. (Agent Observability and Testing / Benchmark Reality Check (real-world tool use))
- awesome-agent-collaborate-tools - Langfuse - Open-source LLM observability (MIT license). Acquired by ClickHouse. 19 Fortune 50 clients. Full-featured: tracing, evaluations, prompt management, datasets. (Observability & Debugging)
- awesome-agi-aci-asi - LangFuse - Open-source LLM engineering platform. Tracing, prompt management, evals, metrics. Self-hostable. 8k+ stars. (LLM Application Frameworks / LLM Observability & Evaluation)
- awesome-ai-pulse-georgia - Langfuse - ების trace-ვა, prompt-ების ვერსირება და LLM-as-a-judge შეფასება ერთ ადგილას. agentic აპლიკაციების production-მონიტორინგისთვის. | (⚙️ ინფერენსი და LLM ხელსაწყოები)
- awesome-ai-testing - Langfuse - Open source LLM observability, tracing, and evaluation platform. (LLM-as-Judge Evaluation)
- awesome-rag - LangFuse - source tool for tracking LLM metrics, observability, and prompt management. (Vendor Examples / Other Tools)
- awesome-opensource-ai - Langfuse - #1 open-source LLM observability platform.  (8. MLOps / LLMOps & Production)
- awesome-observability - Langfuse - Open source LLM engineering platform for observability, metrics, evals, prompt management and datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. (10. LLM & AI Observability / Platforms)
- awesome - 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 (TypeScript)
- awesome-agent-frameworks - Langfuse - Open source LLM engineering platform providing observability, metrics, evals, prompt management, playground, and datasets. (Observability / evals)
- awesome-ai-agents-2026 - Langfuse - `🌱` `[TypeScript]` `[Observability]` - Open-source LLM observability platform for tracing, prompt versioning, and LLM-as-a-judge evaluations. (Safety Guardrails and Observability)
- awesome-production-llm - langfuse
- awesome-mcp-collection - langfuse/mcp-server-langfuse
- awesome-ai-agents - Langfuse - source LLM engineering platform for tracing, prompt management, and evaluations | (⚙️ Agent Operations / 📈 Observability)
- awesome-ai-coding-agent-tools - Langfuse - Open-source observability with tracing, evals, and prompt management. (Supporting Infrastructure / Observability)
- awesome-agent-harness - GitHub - 29442-f4b400?style=flat-square)](https://github.com/langfuse/langfuse) | llmops, tracing, metrics | Open-source LLM engineering platform for traces, metrics, prompts, and evals. | (Catalog / Observability & Reliability Operations)
- awesome-open-source-ai-tools - langfuse/langfuse - 🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. I... (Chatbots & Virtual Companions)
- Awesome-Agentic-Engineering - Langfuse
- awesome-llm-observability - Langfuse
- awesome-ai-agents - Langfuse - source LLM observability. Traces, evals, prompt management. (Agent Infrastructure / Monitoring & Observability)
- awesome-ai-agents - Langfuse
- awesome-auditable-ai - Python, TypeScript - hostable platform for tracing LLM and agent calls, running evaluations, managing prompts, and tracking cost and latency, with OpenTelemetry, LangChain, and OpenAI SDK integrations. MIT-licensed core, 2023-present. (Tools and Platforms / Scanners)
- awesome-agent-orchestration - Langfuse - source LLM engineering platform | (Tools & Infrastructure / Observability & Tracing)
- best_ai_repo_collection - langfuse/langfuse
- awesome-x-ops - Langfuse - source LLM engineering platform for traces, prompt management, evaluations, and metrics. (LLM and Agent Observability)
- awesome-llm-prod - Langfuse - Management | Open-source LLM engineering platform: tracing, evals, prompt management, and metrics | (Evaluation and Observability)
- awesome-llm-cost - Langfuse - Full LLM tracing, prompt management, evaluation, datasets, with token and cost tracking exposed via a metrics API. Self hostable on PostgreSQL and ClickHouse. (Cost Tracking, Observability, and Budgets / Open source)
README

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](https://github.com/ClickHouse/ClickHouse).
> ### 🧑💻 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 hire remotely, with offices in Berlin, San Francisco, Amsterdam, and New York.
> We hire engineers who love open source and great developer experiences.
> **[See open roles →](https://langfuse.com/careers?utm_source=github&utm_medium=readme&utm_campaign=hiring&utm_content=langfuse)**
## ✨ Core Features

- [LLM Application Observability](https://langfuse.com/docs/tracing): 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](https://langfuse.com/docs/demo) to see this in action.
- [Prompt Management](https://langfuse.com/docs/prompt-management/get-started) 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](https://langfuse.com/docs/evaluation/overview) 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](https://langfuse.com/docs/evaluation/dataset-runs/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](https://langfuse.com/docs/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](https://langfuse.com/docs/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

### Langfuse Cloud
Managed deployment by the Langfuse team, generous free-tier, no credit card required.
### Self-Host Langfuse
Run Langfuse on your own infrastructure:
- [Local (docker compose)](https://langfuse.com/self-hosting/local): Run Langfuse on your own machine in 5 minutes using Docker Compose.
```bash
# 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](https://langfuse.com/self-hosting/docker-compose): Run Langfuse on a single Virtual Machine using Docker Compose.
- [Kubernetes (Helm)](https://langfuse.com/self-hosting/kubernetes-helm): Run Langfuse on a Kubernetes cluster using Helm. This is the preferred production deployment.
- Terraform Templates: [AWS](https://langfuse.com/self-hosting/aws), [Azure](https://langfuse.com/self-hosting/azure), [GCP](https://langfuse.com/self-hosting/gcp)
See [self-hosting documentation](https://langfuse.com/self-hosting) to learn more about architecture and configuration options.
#### Docker log rotation
The default `docker-compose.yml` inherits the [Docker daemon's logging configuration](https://docs.docker.com/engine/logging/configure/). Docker's default `json-file` driver does not rotate logs unless configured, which can exhaust disk space. Set its [`max-size` and `max-file` options](https://docs.docker.com/engine/logging/drivers/json-file/), or keep your chosen logging backend and configure retention there. Do not rotate or truncate Docker-managed JSON log files with external tools.
After changing daemon logging defaults, restart Docker and recreate existing containers to apply them; restarting containers alone is insufficient. Plan for interruption and preserve data volumes. These settings cover container stdout/stderr, not database data volumes or ClickHouse's internal log files.
> [!TIP]
> **Self-hosting Langfuse?** Subscribe to the [self-hosting update list](https://langfuse.com/self-hosting#subscribe) to get an email about important features and new releases for open source Langfuse — self-hosting updates only, no marketing.
## 🔌 Integrations

### Main Integrations:
| Integration | Supports | Description |
| ---------------------------------------------------------------------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
| [SDK](https://langfuse.com/docs/sdk) | Python, JS/TS | Manual instrumentation using the SDKs for full flexibility. |
| [OpenAI](https://langfuse.com/integrations/model-providers/openai-py) | Python, JS/TS | Automated instrumentation using drop-in replacement of OpenAI SDK. |
| [Langchain](https://langfuse.com/docs/integrations/langchain) | Python, JS/TS | Automated instrumentation by passing callback handler to Langchain application. |
| [LlamaIndex](https://langfuse.com/docs/integrations/llama-index/get-started) | Python | Automated instrumentation via LlamaIndex callback system. |
| [Haystack](https://langfuse.com/docs/integrations/haystack) | Python | Automated instrumentation via Haystack content tracing system. |
| [LiteLLM](https://langfuse.com/docs/integrations/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](https://langfuse.com/docs/integrations/vercel-ai-sdk) | JS/TS | TypeScript toolkit designed to help developers build AI-powered applications with React, Next.js, Vue, Svelte, Node.js. |
| [Mastra](https://langfuse.com/docs/integrations/mastra) | JS/TS | Open source framework for building AI agents and multi-agent systems. |
| [API](https://langfuse.com/docs/api) | | Directly call the public API. OpenAPI spec available. |
### Packages integrated with Langfuse:
| Name | Type | Description |
| ----------------------------------------------------------------------- | ------------------ | ----------------------------------------------------------------------------------------------------------------------- |
| [Instructor](https://langfuse.com/docs/integrations/instructor) | Library | Library to get structured LLM outputs (JSON, Pydantic) |
| [DSPy](https://langfuse.com/docs/integrations/dspy) | Library | Framework that systematically optimizes language model prompts and weights |
| [Mirascope](https://langfuse.com/docs/integrations/mirascope) | Library | Python toolkit for building LLM applications. |
| [Ollama](https://langfuse.com/docs/integrations/ollama) | Model (local) | Easily run open source LLMs on your own machine. |
| [Amazon Bedrock](https://langfuse.com/docs/integrations/amazon-bedrock) | Model | Run foundation and fine-tuned models on AWS. |
| [AutoGen](https://langfuse.com/docs/integrations/autogen) | Agent Framework | Open source LLM platform for building distributed agents. |
| [Flowise](https://langfuse.com/docs/integrations/flowise) | Chat/Agent UI | JS/TS no-code builder for customized LLM flows. |
| [Langflow](https://langfuse.com/docs/integrations/langflow) | Chat/Agent UI | Python-based UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows. |
| [Dify](https://langfuse.com/docs/integrations/dify) | Chat/Agent UI | Open source LLM app development platform with no-code builder. |
| [OpenWebUI](https://langfuse.com/docs/integrations/openwebui) | Chat/Agent UI | Self-hosted LLM Chat web ui supporting various LLM runners including self-hosted and local models. |
| [Promptfoo](https://langfuse.com/docs/integrations/promptfoo) | Tool | Open source LLM testing platform. |
| [LobeChat](https://langfuse.com/docs/integrations/lobechat) | Chat/Agent UI | Open source chatbot platform. |
| [Vapi](https://langfuse.com/docs/integrations/vapi) | Platform | Open source voice AI platform. |
| [Inferable](https://langfuse.com/docs/integrations/other/inferable) | Agents | Open source LLM platform for building distributed agents. |
| [Gradio](https://langfuse.com/docs/integrations/other/gradio) | Chat/Agent UI | Open source Python library to build web interfaces like Chat UI. |
| [Goose](https://langfuse.com/docs/integrations/goose) | Agents | Open source LLM platform for building distributed agents. |
| [smolagents](https://langfuse.com/docs/integrations/smolagents) | Agents | Open source AI agents framework. |
| [CrewAI](https://langfuse.com/docs/integrations/crewai) | Agents | Multi agent framework for agent collaboration and tool use. |
## 🚀 Quickstart
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.
### 1️⃣ Create new project
1. [Create Langfuse account](https://cloud.langfuse.com/auth/sign-up) or [self-host](https://langfuse.com/self-hosting)
2. Create a new project
3. Create new API credentials in the project settings
### 2️⃣ Log your first LLM call
The [`@observe()` decorator](https://langfuse.com/docs/sdk/python/decorators) makes it easy to trace any Python LLM application. In this quickstart we also use the Langfuse [OpenAI integration](https://langfuse.com/integrations/model-providers/openai-py) to automatically capture all model parameters.
> [!TIP]
> Not using OpenAI? Visit [our documentation](https://langfuse.com/docs/get-started#log-your-first-llm-call-to-langfuse) to learn how to log other models and frameworks.
```bash
pip install langfuse openai
```
```bash filename=".env"
LANGFUSE_SECRET_KEY="sk-lf-..."
LANGFUSE_PUBLIC_KEY="pk-lf-..."
LANGFUSE_BASE_URL="https://cloud.langfuse.com" # 🇪🇺 EU region
# LANGFUSE_BASE_URL="https://us.cloud.langfuse.com" # 🇺🇸 US region
```
```python /@observe()/ /from langfuse.openai import openai/ filename="main.py"
from langfuse import observe
from langfuse.openai import openai # OpenAI integration
@observe()
def story():
return openai.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "What is Langfuse?"}],
).choices[0].message.content
@observe()
def main():
return story()
main()
```
### 3️⃣ See traces in Langfuse
See your language model calls and other application logic in Langfuse.

_[Public example trace in Langfuse](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/db22d0a442216b485abd83cc9df6d9ee)_
## 💭 Support
Finding an answer to your question:
- Our [documentation](https://langfuse.com/docs) is the best place to start looking for answers. It is comprehensive, and we invest significant time into maintaining it. You can also suggest edits to the docs via GitHub.
- [Langfuse FAQs](https://langfuse.com/faq) where the most common questions are answered.
- Use "[Ask AI](https://langfuse.com/docs/ask-ai)" to get instant answers to your questions.
Support Channels:
- **Ask any question in our [public Q&A](https://github.com/orgs/langfuse/discussions/categories/support) on GitHub Discussions.** Please include as much detail as possible (e.g. code snippets, screenshots, background information) to help us understand your question.
- [Request a feature](https://github.com/orgs/langfuse/discussions/categories/ideas) on GitHub Discussions.
- [Report a Bug](https://github.com/langfuse/langfuse/issues) on GitHub Issues.
- For time-sensitive queries, ping us via the in-app chat widget.
## 🤝 Contributing
Your contributions are welcome!
- Vote on [Ideas](https://github.com/orgs/langfuse/discussions/categories/ideas) in GitHub Discussions.
- Raise and comment on [Issues](https://github.com/langfuse/langfuse/issues).
- Open a PR - see [CONTRIBUTING.md](CONTRIBUTING.md) for details on how to setup a development environment.
## 🥇 License
This repository is MIT licensed, except for the `ee` folders. See [LICENSE](LICENSE) and [docs](https://langfuse.com/docs/open-source) for more details.
## Dependencies
We deploy this code base in Docker containers based on the Linux Alpine Image ([source](https://github.com/nodejs/docker-node)). You may find the Dockerfiles in [web/Dockerfile](web/Dockerfile) and [worker/Dockerfile](worker/Dockerfile).
## ⭐️ Star History
## ❤️ Open Source Projects Using Langfuse
Top open-source Python projects that use Langfuse, ranked by stars ([Source](https://github.com/langfuse/langfuse-docs/blob/main/components-mdx/dependents)):
| Repository | Stars |
| :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -----: |
|
[langflow-ai](https://github.com/langflow-ai) / [langflow](https://github.com/langflow-ai/langflow) | 116251 |
|
[open-webui](https://github.com/open-webui) / [open-webui](https://github.com/open-webui/open-webui) | 109642 |
|
[abi](https://github.com/abi) / [screenshot-to-code](https://github.com/abi/screenshot-to-code) | 70877 |
|
[lobehub](https://github.com/lobehub) / [lobe-chat](https://github.com/lobehub/lobe-chat) | 65454 |
|
[infiniflow](https://github.com/infiniflow) / [ragflow](https://github.com/infiniflow/ragflow) | 64118 |
|
[firecrawl](https://github.com/firecrawl) / [firecrawl](https://github.com/firecrawl/firecrawl) | 56713 |
|
[run-llama](https://github.com/run-llama) / [llama_index](https://github.com/run-llama/llama_index) | 44203 |
|
[FlowiseAI](https://github.com/FlowiseAI) / [Flowise](https://github.com/FlowiseAI/Flowise) | 43547 |
|
[QuivrHQ](https://github.com/QuivrHQ) / [quivr](https://github.com/QuivrHQ/quivr) | 38415 |
|
[microsoft](https://github.com/microsoft) / [ai-agents-for-beginners](https://github.com/microsoft/ai-agents-for-beginners) | 38012 |
|
[chatchat-space](https://github.com/chatchat-space) / [Langchain-Chatchat](https://github.com/chatchat-space/Langchain-Chatchat) | 36071 |
|
[mindsdb](https://github.com/mindsdb) / [mindsdb](https://github.com/mindsdb/mindsdb) | 35669 |
|
[danny-avila](https://github.com/danny-avila) / [LibreChat](https://github.com/danny-avila/LibreChat) | 33142 |
|
[BerriAI](https://github.com/BerriAI) / [litellm](https://github.com/BerriAI/litellm) | 28726 |
|
[onlook-dev](https://github.com/onlook-dev) / [onlook](https://github.com/onlook-dev/onlook) | 22447 |
|
[NixOS](https://github.com/NixOS) / [nixpkgs](https://github.com/NixOS/nixpkgs) | 21748 |
|
[kortix-ai](https://github.com/kortix-ai) / [suna](https://github.com/kortix-ai/suna) | 17976 |
|
[anthropics](https://github.com/anthropics) / [courses](https://github.com/anthropics/courses) | 17057 |
|
[mastra-ai](https://github.com/mastra-ai) / [mastra](https://github.com/mastra-ai/mastra) | 16484 |
|
[langfuse](https://github.com/langfuse) / [langfuse](https://github.com/langfuse/langfuse) | 16054 |
|
[Canner](https://github.com/Canner) / [WrenAI](https://github.com/Canner/WrenAI) | 11868 |
|
[promptfoo](https://github.com/promptfoo) / [promptfoo](https://github.com/promptfoo/promptfoo) | 8350 |
|
[The-Pocket](https://github.com/The-Pocket) / [PocketFlow](https://github.com/The-Pocket/PocketFlow) | 8313 |
|
[OpenPipe](https://github.com/OpenPipe) / [ART](https://github.com/OpenPipe/ART) | 7093 |
|
[topoteretes](https://github.com/topoteretes) / [cognee](https://github.com/topoteretes/cognee) | 7011 |
|
[awslabs](https://github.com/awslabs) / [agent-squad](https://github.com/awslabs/agent-squad) | 6785 |
|
[BasedHardware](https://github.com/BasedHardware) / [omi](https://github.com/BasedHardware/omi) | 6231 |
|
[hatchet-dev](https://github.com/hatchet-dev) / [hatchet](https://github.com/hatchet-dev/hatchet) | 6019 |
|
[zenml-io](https://github.com/zenml-io) / [zenml](https://github.com/zenml-io/zenml) | 4873 |
|
[refly-ai](https://github.com/refly-ai) / [refly](https://github.com/refly-ai/refly) | 4654 |
|
[coleam00](https://github.com/coleam00) / [ottomator-agents](https://github.com/coleam00/ottomator-agents) | 4165 |
|
[JoshuaC215](https://github.com/JoshuaC215) / [agent-service-toolkit](https://github.com/JoshuaC215/agent-service-toolkit) | 3557 |
|
[colanode](https://github.com/colanode) / [colanode](https://github.com/colanode/colanode) | 3517 |
|
[VoltAgent](https://github.com/VoltAgent) / [voltagent](https://github.com/VoltAgent/voltagent) | 3210 |
|
[bragai](https://github.com/bragai) / [bRAG-langchain](https://github.com/bragai/bRAG-langchain) | 3010 |
|
[pingcap](https://github.com/pingcap) / [autoflow](https://github.com/pingcap/autoflow) | 2651 |
|
[sourcebot-dev](https://github.com/sourcebot-dev) / [sourcebot](https://github.com/sourcebot-dev/sourcebot) | 2570 |
|
[open-webui](https://github.com/open-webui) / [pipelines](https://github.com/open-webui/pipelines) | 2055 |
|
[YFGaia](https://github.com/YFGaia) / [dify-plus](https://github.com/YFGaia/dify-plus) | 1734 |
|
[TheSpaghettiDetective](https://github.com/TheSpaghettiDetective) / [obico-server](https://github.com/TheSpaghettiDetective/obico-server) | 1687 |
|
[MLSysOps](https://github.com/MLSysOps) / [MLE-agent](https://github.com/MLSysOps/MLE-agent) | 1387 |
|
[TIGER-AI-Lab](https://github.com/TIGER-AI-Lab) / [TheoremExplainAgent](https://github.com/TIGER-AI-Lab/TheoremExplainAgent) | 1385 |
|
[trailofbits](https://github.com/trailofbits) / [buttercup](https://github.com/trailofbits/buttercup) | 1223 |
|
[wassim249](https://github.com/wassim249) / [fastapi-langgraph-agent-production-ready-template](https://github.com/wassim249/fastapi-langgraph-agent-production-ready-template) | 1200 |
|
[alishobeiri](https://github.com/alishobeiri) / [thread](https://github.com/alishobeiri/thread) | 1098 |
|
[dmayboroda](https://github.com/dmayboroda) / [minima](https://github.com/dmayboroda/minima) | 1010 |
|
[zstar1003](https://github.com/zstar1003) / [ragflow-plus](https://github.com/zstar1003/ragflow-plus) | 993 |
|
[openops-cloud](https://github.com/openops-cloud) / [openops](https://github.com/openops-cloud/openops) | 939 |
|
[dynamiq-ai](https://github.com/dynamiq-ai) / [dynamiq](https://github.com/dynamiq-ai/dynamiq) | 927 |
|
[xataio](https://github.com/xataio) / [agent](https://github.com/xataio/agent) | 857 |
|
[plastic-labs](https://github.com/plastic-labs) / [tutor-gpt](https://github.com/plastic-labs/tutor-gpt) | 845 |
|
[trendy-design](https://github.com/trendy-design) / [llmchat](https://github.com/trendy-design/llmchat) | 829 |
|
[hotovo](https://github.com/hotovo) / [aider-desk](https://github.com/hotovo/aider-desk) | 781 |
|
[opslane](https://github.com/opslane) / [opslane](https://github.com/opslane/opslane) | 719 |
|
[wrtnlabs](https://github.com/wrtnlabs) / [autoview](https://github.com/wrtnlabs/autoview) | 688 |
|
[andysingal](https://github.com/andysingal) / [llm-course](https://github.com/andysingal/llm-course) | 643 |
|
[theopenconversationkit](https://github.com/theopenconversationkit) / [tock](https://github.com/theopenconversationkit/tock) | 587 |
|
[sentient-engineering](https://github.com/sentient-engineering) / [agent-q](https://github.com/sentient-engineering/agent-q) | 487 |
|
[NicholasGoh](https://github.com/NicholasGoh) / [fastapi-mcp-langgraph-template](https://github.com/NicholasGoh/fastapi-mcp-langgraph-template) | 481 |
|
[i-am-alice](https://github.com/i-am-alice) / [3rd-devs](https://github.com/i-am-alice/3rd-devs) | 472 |
|
[AIDotNet](https://github.com/AIDotNet) / [koala-ai](https://github.com/AIDotNet/koala-ai) | 470 |
|
[phospho-app](https://github.com/phospho-app) / [text-analytics-legacy](https://github.com/phospho-app/text-analytics-legacy) | 439 |
|
[inferablehq](https://github.com/inferablehq) / [inferable](https://github.com/inferablehq/inferable) | 403 |
|
[duoyang666](https://github.com/duoyang666) / [ai_novel](https://github.com/duoyang666/ai_novel) | 397 |
|
[strands-agents](https://github.com/strands-agents) / [samples](https://github.com/strands-agents/samples) | 385 |
|
[FranciscoMoretti](https://github.com/FranciscoMoretti) / [sparka](https://github.com/FranciscoMoretti/sparka) | 380 |
|
[RobotecAI](https://github.com/RobotecAI) / [rai](https://github.com/RobotecAI/rai) | 373 |
|
[ElectricCodeGuy](https://github.com/ElectricCodeGuy) / [SupabaseAuthWithSSR](https://github.com/ElectricCodeGuy/SupabaseAuthWithSSR) | 370 |
|
[souzatharsis](https://github.com/souzatharsis) / [tamingLLMs](https://github.com/souzatharsis/tamingLLMs) | 323 |
|
[aws-samples](https://github.com/aws-samples) / [aws-ai-ml-workshop-kr](https://github.com/aws-samples/aws-ai-ml-workshop-kr) | 295 |
|
[weizxfree](https://github.com/weizxfree) / [KnowFlow](https://github.com/weizxfree/KnowFlow) | 285 |
|
[zenml-io](https://github.com/zenml-io) / [zenml-projects](https://github.com/zenml-io/zenml-projects) | 276 |
|
[wxai-space](https://github.com/wxai-space) / [LightAgent](https://github.com/wxai-space/LightAgent) | 275 |
|
[Ozamatash](https://github.com/Ozamatash) / [deep-research-mcp](https://github.com/Ozamatash/deep-research-mcp) | 269 |
|
[sql-agi](https://github.com/sql-agi) / [DB-GPT](https://github.com/sql-agi/DB-GPT) | 241 |
|
[guyernest](https://github.com/guyernest) / [advanced-rag](https://github.com/guyernest/advanced-rag) | 238 |
|
[bklieger-groq](https://github.com/bklieger-groq) / [mathtutor-on-groq](https://github.com/bklieger-groq/mathtutor-on-groq) | 233 |
|
[plastic-labs](https://github.com/plastic-labs) / [honcho](https://github.com/plastic-labs/honcho) | 224 |
|
[OVINC-CN](https://github.com/OVINC-CN) / [OpenWebUI](https://github.com/OVINC-CN/OpenWebUI) | 202 |
|
[zhutoutoutousan](https://github.com/zhutoutoutousan) / [worldquant-miner](https://github.com/zhutoutoutousan/worldquant-miner) | 202 |
|
[iceener](https://github.com/iceener) / [ai](https://github.com/iceener/ai) | 186 |
|
[giselles-ai](https://github.com/giselles-ai) / [giselle](https://github.com/giselles-ai/giselle) | 181 |
|
[ai-shifu](https://github.com/ai-shifu) / [ai-shifu](https://github.com/ai-shifu/ai-shifu) | 181 |
|
[aws-samples](https://github.com/aws-samples) / [sample-serverless-mcp-servers](https://github.com/aws-samples/sample-serverless-mcp-servers) | 175 |
|
[celerforge](https://github.com/celerforge) / [freenote](https://github.com/celerforge/freenote) | 171 |
|
[babelcloud](https://github.com/babelcloud) / [LLM-RGB](https://github.com/babelcloud/LLM-RGB) | 164 |
|
[8090-inc](https://github.com/8090-inc) / [xrx-sample-apps](https://github.com/8090-inc/xrx-sample-apps) | 163 |
|
[deepset-ai](https://github.com/deepset-ai) / [haystack-core-integrations](https://github.com/deepset-ai/haystack-core-integrations) | 163 |
|
[codecentric](https://github.com/codecentric) / [c4-genai-suite](https://github.com/codecentric/c4-genai-suite) | 152 |
|
[XSpoonAi](https://github.com/XSpoonAi) / [spoon-core](https://github.com/XSpoonAi/spoon-core) | 150 |
|
[chatchat-space](https://github.com/chatchat-space) / [LangGraph-Chatchat](https://github.com/chatchat-space/LangGraph-Chatchat) | 144 |
|
[langfuse](https://github.com/langfuse) / [langfuse-docs](https://github.com/langfuse/langfuse-docs) | 139 |
|
[piyushgarg-dev](https://github.com/piyushgarg-dev) / [genai-cohort](https://github.com/piyushgarg-dev/genai-cohort) | 135 |
|
[i-dot-ai](https://github.com/i-dot-ai) / [redbox](https://github.com/i-dot-ai/redbox) | 132 |
|
[bmd1905](https://github.com/bmd1905) / [ChatOpsLLM](https://github.com/bmd1905/ChatOpsLLM) | 127 |
|
[Fintech-Dreamer](https://github.com/Fintech-Dreamer) / [FinSynth](https://github.com/Fintech-Dreamer/FinSynth) | 121 |
|
[kenshiro-o](https://github.com/kenshiro-o) / [nagato-ai](https://github.com/kenshiro-o/nagato-ai) | 119 |
## 🔒 Security & Privacy
We take data security and privacy seriously. Please refer to our [Security and Privacy](https://langfuse.com/security) page for more information.
### Telemetry
By default, Langfuse automatically reports basic usage statistics of self-hosted instances to a centralized server (PostHog).
This helps us to:
1. Understand how Langfuse is used and improve the most relevant features.
2. Track overall usage for internal and external (e.g. fundraising) reporting.
The telemetry does not include raw traces, prompts, observations, scores, or dataset contents. We document the exact fields that are collected, where they are sent, and the implementation reference in our [telemetry docs](https://langfuse.com/self-hosting/security/telemetry).
For Langfuse OSS, you can opt out by setting `TELEMETRY_ENABLED=false`.
