← Back toMCP

Memory

Published entries filed under “Memory” in MCP, newest first by publication date on this site.

9 entries

  1. Basic Memory: Markdown notes that you and your agent share

    A local-first memory server where every memory is a Markdown file that you and the agent both edit, with a wikilink graph and semantic search.

    Memory
  2. Context7: current library docs for coding agents

    Upstash's hosted docs service. Coding agents fetch current, version-specific docs and code examples by library name, which cuts stale or invented APIs.

    Memory
  3. deja-vu: memory built from your coding agents’ session history

    Indexes the Claude Code, Codex and Cursor sessions already on your disk so any agent can recall past fixes. Local, one Go binary, no model calls.

    Memory
  4. Hindsight: long-term agent memory that learns from experience

    Vectorize's open-source agent memory service. Retain, recall and reflect turn raw history into consolidated beliefs, with an MCP endpoint per bank.

    Memory
  5. knowledge-rag: offline local document search for Claude Code

    Drop PDFs, Markdown and code into a folder and query them with hybrid search and reranking. Embeddings run locally: no API keys, no external services.

    Memory
  6. MarkItDown MCP: turn PDFs and Office files into Markdown

    Microsoft's official MCP package for MarkItDown. One tool takes a file path or URL and returns Markdown, so agents can read PDFs, Word, slides and spreadsheets.

    Memory
  7. Filesystem MCP: read, write and search files in allowed folders

    One of the official MCP reference servers. Agents read, edit, move and search files only inside folders you allow; every tool carries safety hints.

    Memory
  8. Memory MCP: a local knowledge graph that persists across chats

    The official MCP reference memory server. It stores people, projects and preferences as a small knowledge graph in one local JSONL file.

    Memory
  9. people-context: memory about the people in your life

    A local-first memory server for people: who someone is, how you know them, what you agreed and how they like to talk. One SQLite file, no network calls.

    Memory