Skip to content

upstash/edge-flags

Repository files navigation

Edge Flags

Feature Flags for the Edge

Arch

Note

This project is a Community Project.

The project is maintained and supported by the community. Upstash may contribute but does not officially support or assume responsibility for it.

Edge Flags is a low latency feature flagging solution running at the edge and storing data in a global Redis database. It is designed to be used with Next.js and Vercel but we will soon roll out support for other popular frameworks and platforms. Let us know what you are looking for!

Features

  • Global Low latency: Flags are stored in a global Redis database and are evaluated at the edge.
  • Environments: Flags have different environments to support your deployment process: production, preview and development
  • Flexible: Flags support geo targeting, percentage based rollouts and custom attributes
  • Manage: Flags can be created and managed using the SDK or the self-hosted dashboard in this repo.
  • Free: Edge Flags is free to use. You only pay for the Redis database.
  • Cache: Flags can be cached for a short period of time to reduce the required requests to redis, making it cheaper to use.

Architecture

Arch

Quickstart

  1. Create a redis database

Go to console.upstash.com/redis and create a new global database.

After creating the db, copy the UPSTASH_REDIS_REST_URL and UPSTASH_REDIS_REST_TOKEN to your .env file.

  1. Run npx @upstash/edge-flags-dashboard in your project to open the self-hosted dashboard.
npx @upstash/edge-flags-dashboard

You can also use the hosted version at https://edge-flags-dashboard.vercel.app.

  1. Create a flag from the dashboard. See our docs for more information.

  2. Install @upstash/edge-flags in your project

npm install @upstash/edge-flags
  1. Create an edge function in your project
// /app/api/edge-flags/route.ts
import { createEdgeHandler } from "@upstash/edge-flags";

export const GET = createEdgeHandler({
  cacheMaxAge: 0, // cache time in seconds, 0 disables the cache
  redisUrl: process.env.UPSTASH_REDIS_REST_URL!, // omit to load from env automatically
  redisToken: process.env.UPSTASH_REDIS_REST_TOKEN!, // omit to load from env automatically
});

export const runtime = "edge";
  1. Query the flag in your frontend
// /app/page.tsx
import { useFlag } from "@upstash/edge-flags";

export default function Example() {
  const { isEnabled, isLoading, error } = useFlag("flag-name");

  if (error) return <div>Error: {error}</div>;
  if (isLoading) return <div>Loading...</div>;

  return <div>Is my feature enabled: {isEnabled}</div>;
}

Custom attributes

useFlag accepts an optional object that can be used to pass custom attributes to be evaluated in the flag rules.

const attributes = {
  userId: "chronark",
  role: "admin",
};

useFlag("flag-name", attributes);

Docs

Development

This monorepo is managed by turborepo and uses pnpm for dependency management.

Install dependencies

pnpm install

Build

pnpm build

Database Schema

All configuration is stored in Redis String data types. Each flag is accessible through a key like

STRING
edge-flags:{TENANT}:flags:{FLAG_NAME}:{ENVIRONMENT}

In addition to the flags, there will be a single set that contains all the flag IDs. We can not guarantee the database is only used for edge-flags so we need to keep track of the flags we have created instead of using a potentially expensive SCAN operation.

SET
edge-flags:{TENANT}:flags
  • TENANT is currently unused (set as default) but reserved for future use. ie for managing multiple projects int a single database
  • FLAG_NAME is the unique identifier for the flag
  • ENVIRONMENT is the environment the flag is targeting. ie production, preview, development

Packages

  • /packages/sdk: The SDK to be imported into your project
  • /packages/dashboard: A dashboard for creating and updating your flags
  • /examples/nextjs: An example Next.js app using the SDK

Authors

This project was originally created by