Memory & Knowledge MCP Servers for Codex CLI

MCP server for structured personal data memory with unified source ingestion

Advanced MCP server for RAG-enabled memory through a knowledge graph with vector search

Verifiable Memory for AI Agents — knowledge graph, FTS, Starknet proofs, local or cloud

Long-term memory for AI coding agents: durable project facts, recalled by every MCP client.

Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.

Read, cite, compose and remember over a Markdown knowledge Bundle, as MCP tools over stdio.

Records your Claude Code, Codex and Pi history before deletion. Cited-or-abstain recall.

Persistent memory for Claude Code and Codex. Search and re-inject context from any session.

Local codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

Cryptographically signed visual memory for AI agents. Self-bootstrapping session handoff across any agent.

Save chat notes from Claude Desktop to your vault — MCP on Obsidian CLI. Keep what matters.

MCP server for the Thorbit Knowledge Graph entity-linking pipeline

Memoria personal para Claude Code en notas Markdown; no carga el contexto a ciegas.

Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware, secret-safe

Persistent codebase intelligence that gives AI assistants memory across sessions

Local agent memory, coding loop, Cursor from Telegram, scheduled playbooks, and MCP tools.

Persistent developer memory MCP server — the LLM is stateless, Mnestra isn't

Claude Desktop MCP server for MousaiNote — save/search/browse memos, manage folders, and attach files from Claude conversations.

StremAI MCP: shared memory for AI coding agents. OAuth-first hosted MCP with a local stdio fallback for Claude Code, Codex, Cursor, and

Opinionated MCP for Bear Notes. Relevance-ranked search across titles, bodies, hierarchical tags. Offline-first.

LatentContext MCP Server — Intelligent memory and context management for LLMs