How Migration Works
Every migration kit runs in two phases:- Flag definitions: The kit reads your flags, targeting rules, and rollout percentages from the source platform and recreates them in Confidence.
- Code transformation: The kit rewrites your application code from the source platform’s SDK to OpenFeature with the Confidence SDK, creating one pull request per flag.
plan flaggenerates a migration plan for your flag definitionsplan codegenerates a migration plan for your code changesexecute <plan-file>carries out the plan you generated
Install the Confidence Plugin
- Claude Code
- Cursor
- Codex
- Gemini CLI
Before You Begin
To run any migration kit, you need:- A Confidence account with a client to resolve flags
- The Confidence Flags MCP server, authenticated with your account—see the Use AI with Confidence quickstart
- The Confidence Documentation MCP server, used during code transformation
- Read access to your source platform, typically an API key—see each migration kit page for details
Migration Kits
Migrate from PostHog
Move feature flags and multivariate flags with the
/confidence:migrate-posthog command.Migrate from Eppo
Move feature flags, allocations, and audiences with the
/confidence:migrate-eppo command.Migrate from Statsig
Move feature gates, dynamic configs, and experiments with the
/confidence:migrate-statsig command.Migrate from Optimizely
Move flags, rulesets, and audiences with the
/confidence:migrate-optimizely command.The plugin also includes skills for onboarding new Confidence accounts and setting up a data warehouse connection. See the plugin repository for the full list.
Related Resources
Use AI with Confidence
Set up the Confidence MCP servers for your AI assistant
MCP Servers Reference
Complete reference for all MCP tools and capabilities
Analyze a Past Experiment
Re-analyze experiments that ran on another platform
SDK Integration
Integrate Confidence SDKs into your application

