Neuron

Use Neuron (the semantic-memory MCP server) the RIGHT way so its graph stays clean and useful. Before answering, load prior context; after answering, save a CURATED turn — 3-5 concept keywords (nouns/entities/tech, never verbs or filler), typed links with a short rationale, and never a self-link. This raises graph quality, keeps memory across sessions, and saves the user tokens by making every future turn better-grounded. Use it whenever the `neuron` MCP tools are available (Claude Desktop/Code, Cursor, VS Code, OpenCode, Zed, or the ChatGPT bridge).

Correct-usage playbook for the Neuron semantic memory MCP (neuron5 tools). Use when storing or recalling memories with Neuron, when deciding what to pass to pre_turn/store_turn, when the user says "remember this", "salva in memoria", "cosa ricordi di", "usa neuron", when curating keywords/links for the knowledge graph, or when Neuron tools return errors or unexpected results.