What problem does it solve? Moving an existing project from the self-hosted mem0 OSS SDK (the local Memory class with vector store, embedder, and LLM config) to the hosted mem0 Platform (MemoryClient) involves many subtle API differences, and a missed call site or wrong parameter causes runtime breaks. This Skill audits every mem0 usage in a repo, writes a reviewable migration plan, and executes it only after approval. ## Core Features & Use Cases - Full Footprint Discovery: Finds every mem0 import, client initialization, config block, call site, dependency, env variable, and local infra service across Python and TypeScript codebases. - Verified API Mapping: Confirms real method signatures against the installed SDK version and maps each OSS call to its hosted equivalent (filters, top_k/topK, pagination), flagging non-1:1 cases like graph memory, custom prompts, and reset(). - Plan-Then-Execute Workflow: Writes a concrete MEM0_MIGRATION_PLAN.md with inventory, change set, concerns, and verification steps, then executes and smoke-tests against the hosted API after the developer approves. - Use Case: A team running a RAG service with Memory.from_config backed by a local Qdrant wants to switch to the managed platform; the Skill produces the plan, swaps the client, updates dependencies and env, and verifies with a real MEM0_API_KEY. ## Quick Start Ask your assistant to migrate this project's mem0 setup from the self-hosted OSS SDK to the hosted mem0 Platform using MemoryClient.
