$ loading_
Stores approved corrections and preferences so agents avoid repeating mistakes.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Changes Memory MCP" yet — see the docs or source repo.
Save this user preference to project memory: when replying with code examples, prefer TypeScript and keep responses concise.
Writes reusable project memory for later retrieval.
Search memories related to API naming conventions and error handling, then list the most relevant entries.
Returns relevant memory entries to help the model follow existing rules.
Developers often need to retain approved corrections and preferences across long collaboration sessions. This tool stores them and makes them easy to retrieve later.
Use global memory for rules that apply everywhere, and project memory for project-specific conventions, making memory management cleaner.
It is a local MCP server that stores user-approved corrections, preferences, and reusable criteria in Markdown files. It also supports global and project memory, plus list, search, and retrieve tools.
It is designed for agent workflows, focusing on making approved, reusable rules easy for AI to retrieve and apply. Ordinary notes usually do not provide that retrieval-oriented structure.
The provided material only states that it is a local MCP server and does not specify further installation or runtime requirements; see the source repository.
Safely read, write, and search a local Markdown memory store via MCP.
Give MCP clients durable memory for recalling user and project context.
Enable AI clients to remember user preferences across conversations with vector search.
Give AI agents persistent memory and semantic retrieval across conversations.
Provide shared cross-session memory storage, retrieval, and governance for MCP AI tools.
Give AI agents persistent knowledge-graph memory and cross-session retrieval.