What is Fency

Fency is a flexible and developer-friendly framework for getting AI features into production. It currently supports any backend and webapps built on React (more webapp libraries coming soon).

How it works

Under the hood, Fency orchestrates three things: your data, access control, and the client-side experience.

Your backend

1. Syncs data into Fency as Memories
2. Creates Sessions with scoped access to specific memories
3. Hands a short-lived client token to the frontend

Your webapp (using @fencyai/react)

1. Calls your backend to fetch the scoped access client token
2. Calls the Fency API to start agent tasks using the client token
3. Streams responses and renders progress in real time

Core concepts

• Memories: Made for mirroring your data into Fency. Your backend creates and updates memories via the Fency API (POST /v1/memories, PATCH /v1/memories/:id). Memories support text, URL, and file sources, and can be used for RAG, context injection, and more. Learn more in Memories.
• Sessions: Control access to memories and API usage. Your backend creates sessions with a secret key; the client receives a short-lived clientToken. Guardrails limit which memories a task may see; allowed actions limit which actions and components it may declare; background and examples steer Explore Memories; a conversation groups Explore Memories and Explore Product tasks. The client token cannot widen these limits. Learn more in Sessions.
• Agent tasks: The work the webapp starts with a createAgentTask client token: chat, memory search, explore memories, or explore product. Your server does not start the task; it only decides which task type and limits the session allows. Learn more in Agent tasks.
• @fencyai/react SDK: Orchestrates the flow and renders progress in the webapp. It handles token fetching, session creation, streaming, and UI state — tying your backend, the Fency API, and React together. See Integration examples for setup.

End-to-end flow

The diagram below shows how your backend syncs memories to Fency, then how the React SDK obtains a client token and makes API requests. See Sessions and Integration examples for implementation details.