Memory & Knowledge MCP Servers for Grok Build

Secure, fragment-based long-term memory for MCP-compatible AI agents.

Local hybrid-search memory for AI agents over plain Markdown. Multi-tenant, offline, no LLM.

Local semantic search over your Obsidian vault - always fresh, never reindex.

MCP Server for Memvid

Persistent Memory Kernel for AI Agents — crash recovery, shared memory, audit trail, real-time dashboard

Local-first intent and provenance for Codex, Claude Code, Cursor, Gemini CLI, and MCP agents.

Feynman's twelve-problems method as an MCP server: dormant problems + an evoke loop for new tricks.

Decision memory for AI coding agents: captures decisions once, briefs every agent before it acts.

Automatic project memory for Claude Code. Also works with Cursor and Codex.

MCP server for AutoMem: AI memory storage and recall

Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 30 MCP

Persistent file-based memory for AI agents: inspectable, versionable, fully local.

Search, read and act on Apple Notes — folders, attachments, writes off by default

Local-first, cross-harness memory for AI coding agents.

Persistent institutional memory for AI coding agents. Memory that compounds.

Project memory and a control plane for AI coding agents.

Persistent memory and context for your agent, on a board you can see. Capped, so it stays small.

MCP server for mneme: 9 tools for vault-native memory in Claude Code and MCP-compatible clients.

MCP Server for AI Agent Memory - persistent, semantically-searchable memory for AI agents

AI session memory: the brief your AI reads before every session so no session starts cold.

Persistent agent memory as plain Markdown in your repo - readable, diffable, with provenance.