"Exploring Memory Persistence in DeepSeek Technology" matching MCP servers:

Enables persisting chat-thread notes to SQLite with upsert semantics, allowing creation, update, retrieval, and listing of per-user threads via MCP tools.

Enables AI assistants to retain, review, approve, and retrieve encrypted local notes, decisions, preferences, and follow-ups across sessions, with retained source evidence and correction history.

Enables AI assistants to maintain a persistent, local memory using SQLite with ranked full-text search, German morphological matching, and two-axis filing, all without external services.

Lets AI clients store, retrieve, update, and forget long-term facts in a local SQLite database with deterministic lexical search, sharing the same memory across multiple clients without relying on model APIs or embedding services.

A notes app that becomes your second brain. Open source, private, encrypted when you want it, and every file stays yours. Mac, Windows, Linux and self host!

Automatically records AI conversation turns and code changes to local Markdown files to provide persistent context across chat sessions. It enables AI agents to search history through MCP tools and provides a web viewer for browsing past discussions.

Provides cross-session persistent memory for coding agents via MCP tools to store, retrieve, and manage notes with hybrid keyword/semantic search and automatic deduplication.

A lightweight MCP server that provides persistent knowledge graph storage for AI assistants, enabling memory across sessions through entity-relationship storage with JSON file persistence.

Stores markdown knowledge notes in SQLite or Postgres and exposes them to AI agents over MCP, letting agents read individual sections, search, and write updates transactionally. Each write is validated, and anything that introduces broken links, missing summaries, or duplicate text is rolled back with a reason.

A local MCP server that provides agents with tools to list, read, search, inspect history and diffs, and capture unstructured text in a user-owned Git repository of durable memory.

Local-first agentic knowledge layer over Obsidian notes, enabling MCP-aware agents to search, retrieve, and compile knowledge with provenance and task contracts.

Enables read-only cognitive retrospect over Obsidian notes, surfacing stance changes, verifying claims with citable evidence, and avoiding unfounded causal stories via hybrid retrieval and eight read-only MCP tools.

An MCP server that lets users capture quick phone thoughts via Android and later query them from AI assistants like Grok or Claude, functioning as a simple task memory store without notifications or geolocation.

Personal memory MCP server for Claude Code with an Obsidian-style graph. Enables persistent, queryable memories across sessions using Markdown files with bidirectional wiki-links and a D3.js force-directed graph UI.

Enables AI assistants to maintain persistent local memory across sessions by organizing experiences into hierarchical layers (raw logs, checkpoints, daily cards, and stories), with tools to write, search, and verify entries via hashes.

Enables AI agents to search and manage a local Markdown memory vault over stdio, including hybrid search, note retrieval and addition, session handoff claiming, and status checks without holding a model in memory.

Provides curated long-term memory for Codex CLI via MCP, with Markdown-based storage, deduplication, and decay-based forgetting.

Persistent memory management for Claude Code, allowing agents to store and retrieve user preferences, environment notes, and skills across sessions.

This MCP server lets coding agents read and write a plain-markdown wiki, then audits that memory and local session transcripts to produce drift reports, session digests, and reusable lessons.

Enables project-scoped persistent linked memory for OpenCode V2, providing nine MCP tools for recall, update, pin, link, and read operations on notes within isolated projects.

Enables reading, writing, and searching a local markdown-based memory store using MCP tools, with safety checks and index consistency.

Enables AI agents to keep and query long-term memory of past conversations, with hybrid keyword-plus-semantic search, session, day, week, month and year summaries, saved notes, and a running set of current facts about the user. Exposes this over MCP streamable HTTP through five tools so any client can retrieve context that would otherwise be lost between sessions.

Enables AI assistants to retain memory across sessions by storing conversations locally in Markdown files, allowing personalization and continuity without external servers.

Enables AI clients to preserve and share knowledge as plain Markdown files in a local folder the user owns, with tools to remember, recall, get, update, forget, and list scopes. Memories are stored by scope, versioned rather than overwritten, and readable or editable in Obsidian or any text editor.

Provides a persistent memory layer for Claude coding assistants so context, decisions, and progress survive session resets and compaction. Enables saving, searching, checkpointing, and restoring context across sessions through channels, categories, git integration, and batch operations.

Gives any MCP-capable AI agent long-term memory from a self-hosted Obsidian vault, exposing tools to read, search, list and write markdown notes over MCP or a REST API with keyword plus semantic search. Agent writes are confined to a drafts inbox so they never overwrite your own notes.

Provides AI agents with persistent memory and cross-session archive management using IMA notes and knowledge bases. It enables memory storage, search, updating, session saving, and shared memory across any MCP-compatible client.

Serves a git-backed folder of Markdown notes over MCP so AI agents can search, read, write, move and delete them, with every write recorded as a git commit attributed to the calling client. Supports full-text section search with snippets, wikilinks and typed relations, LFS-backed searchable attachments, optimistic concurrency for multiple agents, and per-client token or OAuth 2.1 access.

Enables AI agents and any MCP-compatible client to persist, search, update, and delete plain-text memories across sessions, using BM25 lexical ranking over SQLite FTS5 with namespace filtering, tags, free-form metadata, and JSONL export/import — entirely local, with zero external infrastructure.

A personal memory MCP server for Claude Code that stores and retrieves memories via natural language, supporting text, images, files, and secrets with vector search.