Base
Hardened build
minimal ports, security patches applied at build time
Cognee
Azure
Artificial Intelligence (AI)
1 variation
an open source AI memory engine that turns your documents into a knowledge graph you can query
Variations
This product is available in the build below. Open it for the operating system, cloud and version detail, or read its deployment guide.
| Product | Cloud | Operating system | Version | |
|---|---|---|---|---|
| Cognee on Ubuntu 24.04 | Azure | Ubuntu 24.04 | Standard | View · Guide |
Overview
Cognee is an open source AI memory engine. You give it documents, notes, transcripts or web pages and it uses a language model to extract the people, organisations, products and events in them and the relationships between them into a knowledge graph, while embedding the same text into a vector store. Questions are then answered from the graph and the vectors together, so an answer can follow how facts connect across your sources instead of returning whichever paragraph merely looked similar. A web interface lets you add data, browse datasets, explore the graph as a mind map and search it, and everything is also available over a documented REST API with per user API keys, so agents and applications can use it as long term memory. Storage is embedded: SQLite for metadata, LanceDB for vectors and an embedded graph database, so there is no database server to run.
Why the cloudimg image
The cloudimg image works with no API key on arrival: it bundles a local open source language model served by Ollama on the CPU and a local embedding model, both pinned by checksum, so your data never leaves the VM unless you choose a hosted provider. Switching to your own provider key for faster processing is one configuration change. It is secure by default: authentication is enforced, every launch generates its own admin password and signing secrets at first boot and proves the old default password is refused before anything is served, the web interface and API sit behind nginx on HTTPS with a certificate generated for that VM, public self registration is closed, and the application, its interface and the model server listen only on the loopback address. The application cannot reach the Azure instance metadata service or the platform wire server, and the model server only answers the application. Every component is built from pinned open source releases, with dependency licence inventories shipped on the instance, and 24/7 cloudimg support is included.
Common uses
- Give an AI agent persistent memory of documents and past conversations
- Build a private knowledge graph over research notes, policies or manuals
- Ask grounded questions across sources without sending data to a hosted model
More in Artificial Intelligence (AI)
Agent Zero
Artificial Intelligence (AI)
Agent Zero, the open source AI agent that writes and runs code, browses the web and uses tools inside its own Linux work
Argilla
Artificial Intelligence (AI)
Argilla, an open source data annotation and curation platform for building high quality datasets for natural language pr
Bifrost
Artificial Intelligence (AI)
one OpenAI compatible endpoint in front of every model provider, packaged by cloudimg
ContextForge MCP Gateway
Artificial Intelligence (AI)
ContextForge, the open source model context protocol gateway from IBM: federate many MCP servers behind one authenticate
Crawl4AI
Artificial Intelligence (AI)
an open source web crawler that turns any web page into clean, LLM ready markdown over a REST API, secured from first bo
Do
DeepWiki-Open
Artificial Intelligence (AI)
turn any Git repository into a browsable, AI generated wiki