Memory & Knowledge MCP Servers for Codex CLI

MCP server for semantic memory storage using local Postgres with pgvector

The markdown workspace your AI can read, search, and suggest edits in — every change signed.

Chinese-first AI Agent technical knowledge memory MCP Server

Persistent episodic memory for AI coding: capture, retrieve, brief, dream cycle, cross-project.

Shared memory MCP server for AI coding agents — local by default, team-shared via threadctx.dev.

MCP server for Trilium Notes - Provides LLM access to your notes

Git-native, review-gated knowledge base for LLM agents. MCP server + CLI.

Neo4j-native DIKW memory for Claude Code — knowledge that compounds across sessions

Model Context Protocol server for accessing Wolai workspace content.

MCP Server for AI Books - Universal LLM context extension via gravitational memory compression

Local-first persistent memory for AI agents. SQLite + hybrid search (keyword + local vector embeddings). Zero API costs. Works with Claude

Read, publish and explore creative bisociations between concepts on unbancodeideas.com.

Chitta - permission-aware memory for AI agents: a knowledge-graph + vector memory MCP server + SDK with per-user access control. Runs on

MCP server for AI-powered codebase indexing with auto-save checkpoints, incremental updates, real-time progress tracking, and index

Hard state for AI agents: typed, governed, durable state with deterministic queries, governed writes, and receipts.

MCP server for Dify knowledge base retrieval

Local-first MCP server serving a project's business-domain knowledge to MCP-compatible agents.

Semantic search MCP server for Claude Code conversation sessions

Persistent memory for AI native teams. Shared memory across Claude Code, Cursor, Codex, and self-hosted LLMs via MCP.

MCP server for AI knowledge repository (rules, skills, workflows, agents, commands, templates)

MCP server for Hookmark — exposes the hook CLI as MCP tools for Claude Code