---
title: "Langfuse Integration with Cognee"
sidebarTitle: Cognee
logo: /images/integrations/cognee_icon.png
description: "Monitor Cognee pipelines and AI memory with Langfuse for comprehensive observability in your AI agents."
category: Integrations
---

# Cognee Integration with Langfuse

> **What is Cognee?** [Cognee](https://www.cognee.ai/) is an open-source AI memory that turns your data into a searchable, reasoning-ready knowledge graph. By pairing Cognee with Langfuse you gain production-grade tracing, evaluation, and analytics for every pipeline step, and search query. Check out the [GitHub repo](https://github.com/topoteretes/cognee) or the [docs](https://docs.cognee.ai) for details.

> **What is Langfuse?** [Langfuse](https://langfuse.com) is the open-source AI engineering platform. It helps teams trace applications, debug issues, evaluate quality, and monitor costs in production.

## Quick Start Guide

<Steps>

### Step&nbsp;1: Install Cognee (includes Langfuse)

```bash
pip install cognee  # langfuse is declared as a dependency and will be installed automatically
```

### Step&nbsp;2: Create a Langfuse Project

1. Sign up at [Langfuse Cloud](https://cloud.langfuse.com).
2. Create a new project and copy your **public** and **secret** API keys.

### Step&nbsp;3: Configure Environment Variables

Create a `.env` file or export the variables directly in your shell:

```txt filename=".env"
LANGFUSE_PUBLIC_KEY=<your public key>
LANGFUSE_SECRET_KEY=<your secret key>
LANGFUSE_HOST=https://cloud.langfuse.com   # 🇪🇺 EU region
# Other Langfuse data regions include 🇺🇸 US: https://us.cloud.langfuse.com, 🇯🇵 Japan: https://jp.cloud.langfuse.com and ⚕️ HIPAA: https://hipaa.cloud.langfuse.com
```

### Step&nbsp;4: Trace Cognee Functions

`cognee` ships with a tiny wrapper around Langfuse. Import `get_observe()` and decorate any function you want to monitor.

```python
from cognee.modules.observability.get_observe import get_observe

observe = get_observe()

@observe(as_type="generation")  # optional label
async def acreate_structured_output(...):
    ...  # your business logic
```

Every time the function runs, the decorator automatically opens a **span** in Langfuse and streams metrics such as duration, token usage, and custom metadata.

### Step&nbsp;5: Start Cognifying & Watch Traces

Run your regular Cognee workflows:

```python
import cognee
import asyncio
from cognee.modules.observability.get_observe import get_observe

observe = get_observe()

@observe(name="simple_example_run", as_type="example")
async def main():
    await cognee.add("Natural language processing (NLP) is ...")
    await cognee.cognify()
    results = await cognee.search("Tell me about NLP")
    for r in results:
        print(r)

asyncio.run(main())
```

Open the Langfuse UI – traces for any `@observe`-decorated helper functions will appear.

</Steps>

## Adding Your Own Spans

You can instrument **any** function in your codebase – not just cognee internals:

```python
from cognee.modules.observability.get_observe import get_observe

observe = get_observe()

@observe(as_type="my_tool", metadata={"foo": "bar"})
def my_helper(arg1, arg2):
    ...
```

## Resources

- [Cognee homepage](https://www.cognee.ai/)
- [Cognee GitHub repository](https://github.com/topoteretes/cognee)
- [Cognee docs](https://docs.cognee.ai/how-to-guides/cognee-sdk/integrations/langfuse-integration) for this integration

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/integrations/other/cognee.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.