# cognee
AI Applications and RAGs - Cognitive Architecture, Testability, Production Ready Apps
Open-source framework for building and testing RAGs and Cognitive Architectures, designed for accuracy, transparency, and control.
[//]: # (Follow PromethAI
)
[//]: # ()
[//]: # ()
[//]: # (
)
[//]: # ()
[//]: # (
)
[//]: # (
)
[//]: # (
)
[//]: # (
)
[//]: # (
)
Share cognee Repository
[Star us on Github!](https://www.github.com/topoteretes/cognee)
Jump into the world of RAG architecture, inspired by human cognitive processes, using Python.
[cognee](www.cognee.ai) runs in iterations, from POC towards production ready code.
To read more about the approach and details on cognitive architecture, see the blog post: [AI Applications and RAGs - Cognitive Architecture, Testability, Production Ready Apps](https://topoteretes.notion.site/Going-beyond-Langchain-Weaviate-and-towards-a-production-ready-modern-data-platform-7351d77a1eba40aab4394c24bef3a278?pvs=4)
Try it yourself on Whatsapp with one of our [partners](www.keepi.ai) by typing /save _content_ followed by /query _content_
### Get Started in Moments
Running [cognee](www.cognee.ai) is a breeze. Simply run `cp env.example .env` and `docker compose up cognee` in your terminal.
Send API requests add-memory, user-query-to-graph, document-to-graph-db, user-query-processor to the locahost:8000
### Current Focus
#### Integration to keepi.ai and other apps
Uses Neo4j to map user preferences into a graph structure consisting of semantic, episodic, and procedural memory.
Fetches information and stores information and files on Whatsapp chatbot using [keepi.ai](www.keepi.ai)
Uses the graph to answer user queries and store new information in the graph.
### Architecture

### How Cognee Enhances Your Contextual Memory
Our framework for the OpenAI, Graph (Neo4j) and Vector (Weaviate) databases introduces three key enhancements:
- Query Classifiers: Navigate information graph using Pydantic OpenAI classifiers.
- Document Topology: Structure and store documents in public and private domains.
- Personalized Context: Provide a context object to the LLM for a better response.