---
slug: "langfuse"
name: "Langfuse"
effect: "Traces LLM calls and agent steps, then runs evals, datasets and prompt versioning on top of them"
category: "eval-observability"
tier: "standard"
url: "https://langfuse.com"
github: "langfuse/langfuse"
pricing: "open-source"
license: "MIT; ee/ directories under a separate enterprise license"
tags: ["tracing", "evals", "prompt-management", "self-hosted", "python", "typescript"]
platforms: ["docker"]
install_kind: "pip"
date_added: "2026-10-14"
rank: null
rising_score: 55
stars: 35838
star_velocity: 28.8
velocity_basis: "since creation"
created_at: "2023-05-18T17:47:09Z"
pushed_at: "2026-10-15T04:56:34Z"
signals_status: "ok"
signals_fetched_at: "2026-10-15T05:02:43.393Z"
page: "https://agenttooldrop.com/tools/langfuse"
---

# Langfuse

Traces LLM calls and agent steps, then runs evals, datasets and prompt versioning on top of them

Category: Evals and observability. Tier: standard (a well-known tool, listed for reference, not ranked). Pricing: Open source. License: MIT; ee/ directories under a separate enterprise license.

Platforms: docker.

## Why you would want it

Langfuse instruments an app through Python and JS/TS SDKs or integrations such as the OpenAI SDK, LangChain, LlamaIndex, Vercel AI SDK and Mastra, and records LLM calls, retrieval and agent actions as traces you can inspect. The same platform covers prompt management with server and client caching, datasets for pre-deployment tests, and evaluations via LLM-as-a-judge, code evaluators, user feedback and manual labeling. You can use Langfuse Cloud or self-host it with Docker Compose, on a VM or on Kubernetes via Helm.

## Best for

- Teams that want to self-host LLM observability
- Tracing, prompts and evals in one place
- Python and JS/TS stacks

## Use it when

You need to see what your LLM app or agent did on each request and want to evaluate and iterate on prompts against the same traces.

## Skip it if

You do not want to run a server stack yourself and cannot use a hosted account; self-hosting means running the Docker Compose or Kubernetes deployment. Code under the ee/ directories is not MIT licensed.

## Install

Install the Python SDK:

```sh
pip install langfuse
```

Source: https://langfuse.com/docs/observability/sdk/overview

## Live signals

Fetched 2026-10-15T05:02:43.393Z (status: ok).

- Repository: langfuse/langfuse
- Repository created: 2023-05-18
- Stars: 35,838 (GitHub's count; it cannot be authenticated)
- Stars per day, since repo creation: 28.8 (an average over the repo's life, not a growth rate)
- Forks: 3,992
- Open issues and PRs: 1,059
- License (GitHub): NOASSERTION
- Last push: 2026-10-15
- Latest release: v4.59.0 (2026-10-14)

## Links

- Website: https://langfuse.com
- GitHub: https://github.com/langfuse/langfuse
- Install instructions verified at: https://langfuse.com/docs/observability/sdk/overview
- Source for this entry: https://github.com/langfuse/langfuse#readme
- AgentToolDrop page: https://agenttooldrop.com/tools/langfuse
- Full catalog (JSON): https://agenttooldrop.com/tools.json