Cognee | Respan Docs

Cognee is an open-source memory engine with a semantic graph at its core that provides observability for AI agents and semantic workflows. The Cognee–Respan integration patches Cognee’s @observe decorator so every task and workflow run becomes a Respan span automatically.

Set up Respan

Create an account at platform.respan.ai and grab an API key.

Run npx @respan/cli setup to set up with your coding agent.

Resources

Tracing

Setup

Install packages

$ pip install respan-ai cognee-community-observability-respan

Set environment variables

$ export MONITORING_TOOL="respan"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
$ export LLM_API_KEY="YOUR_OPENAI_API_KEY"

MONITORING_TOOL=respan tells Cognee to use Respan as its observability backend. LLM_API_KEY is required if your pipeline calls LLMs.

Initialize and run

1 import asyncio
2 import cognee_community_observability_respan  # noqa: F401 — patches Cognee on import
3 from cognee.modules.observability.get_observe import get_observe
4 
5 observe = get_observe()  # returns Respan-backed decorator
6 
7 @observe
8 def process_documents(documents: list[str]):
9     return [f"Processed: {doc}" for doc in documents]
10 
11 @observe
12 def create_knowledge_graph(processed_docs: list[str]):
13     return [{"id": i, "content": doc} for i, doc in enumerate(processed_docs)]
14 
15 @observe(workflow=True)
16 async def semantic_workflow():
17     documents = ["Document 1", "Document 2", "Document 3"]
18     processed = process_documents(documents)
19     return create_knowledge_graph(processed)
20 
21 result = asyncio.run(semantic_workflow())
22 print(f"Created knowledge graph with {len(result)} nodes")

View your trace

Open the Traces page to see your Cognee workflow with task spans, knowledge graph operations, and LLM calls.

How it works

The Respan integration patches Cognee’s get_observe() at import time so:

@observe maps to Respan’s task() decorator.
@observe(workflow=True) maps to Respan’s workflow() decorator.
Telemetry is initialized once via RespanTelemetry() on import.

Configuration

Variable	Description	Required
`MONITORING_TOOL`	Set to `respan`	Yes
`RESPAN_API_KEY`	Your Respan API key	Yes
`LLM_API_KEY`	Your LLM provider API key	Optional

Custom span names

1 @observe(name="custom_task_name")
2 def my_task():
3     pass
4 
5 @observe(workflow=True, name="custom_workflow_name")
6 async def my_workflow():
7     pass

Troubleshooting

Issue	Solution
No traces	Ensure `RESPAN_API_KEY` is set and `MONITORING_TOOL=respan`.
Decorators don’t fire	Import `cognee_community_observability_respan` before calling `get_observe()`.