Welcome to DeepFellow Docs
DeepFellow is a private AI framework allowing software teams to deliver compliant, auditable, and scalable AI – tailored to the most demanding sectors.
Why DeepFellow?
Unlike SaaS LLMs, DeepFellow runs entirely within your environment, adapts to your internal knowledge, and scales with your operations without exposing sensitive information or compromising auditability. You decide which data the system learns from, how it is accessed, and where it runs.
Quickstart
DeepFellow Workspace
DeepFellow Workspace is a private, source-grounded AI tool designed to help you work with your own documents and knowledge resources. It runs on top of a DeepFellow Server project, which gives it access to the models served by DeepFellow Infra.
Key Elements
DeepFellow Server
The gateway to access MCP servers, Tools, DeepFellow Infra, Plugins, and Vector Stores. It also provides authorization and administration layers to the system, and is used for all the other application-related operations.
DeepFellow Infra
A self-hosted infrastructure stack purpose-built to run AI on your own hardware. It provides the compute foundation for LLMs, embedding models, MLAs, and MCP servers – giving you full ownership of the environment without relying on third-party cloud APIs.
DeepFellow CLI
The DeepFellow command line interface. Use it to install, configure, and manage DeepFellow Infra and Server.
Nightshift
A background worker that runs document-heavy features, like Metadata Expansion and Document Summarization, asynchronously so requests return immediately.
Threat Intelligence
Coming soon – protecting your AI system from modern, AI-specific attack vectors, like prompt injection, data poisoning and model inversion attacks.
Dashboard
Coming soon – lets you manage, monitor and observe the entire AI stack in one web dashboard.
We use cookies on our website. We use them to ensure proper functioning of the site and, if you agree, for purposes such as analytics, marketing, and targeting ads.