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 convention causes runtime breaks. This Skill audits every mem0 touchpoint, writes a reviewable migration plan, and executes it only after approval.
Core Features & Use Cases
- Full Footprint Discovery: Scans the repo for mem0 imports, client initialization, config blocks, call sites, dependencies, env variables, and local infrastructure such as Qdrant containers.
- Verified API Mapping: Confirms real method signatures against the installed SDK and maps each OSS call to its hosted equivalent for both Python and TypeScript, including
filters, top_k/topK, and pagination changes.
- Plan-Then-Execute Workflow: Writes a concrete
MEM0_MIGRATION_PLAN.md with an inventory, change set, concerns, and verification plan, then executes the edits and runs a real-API smoke test 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 add/search/delete_all against the hosted API.
Quick Start
Ask your AI assistant to migrate your project's mem0 setup from the self-hosted OSS SDK to the hosted mem0 Platform using your MEM0_API_KEY.
