Memory & Knowledge MCP Servers for Codex CLI

Agentic memory for cyber threat intelligence. STIX graphs, actor aliasing, offline RAG, Sigma/YARA.

Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.

Cross-LLM persistent memory: store context once, recall it from any AI model.

Persistent memory server backed by DuckDB.

Governed memory for AI agents. Memory with receipts. Local, plain files, zero network calls.

Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.

Persistent memory for AI agents — local JSON, zero config, no server required.

MCP server bridging context between Claude Chat, Code, and Cowork

EnvMem - Personal environment variable memory with semantic search. Store, search, and manage your environment variables with AI-powered

MCP server giving AI agents persistent SQLite memory that proves which lessons hold.

Living technical memory for AI agents: recall approved project context, record what was learned.

MCP server for Gemini RAG — manage File Search stores, upload documents, and query with AI-powered retrieval-augmented generation

MCP Memory Server with Neo4j backend for AI knowledge graph storage

Independent, reproducible benchmark harness for agent-memory backends.

Stop re-explaining yourself to AI. Save knowledge once, use it in every conversation.

Persistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.

MCP server for indexing and searching Claude Code conversation history with decision tracking, git integration, and project migration/merge

A self-improving, verifiable memory layer for AI coding agents.

MCP server for AI-native project context management

Team Project Memory skill for shared AI agent project knowledge, plus the ContextEngine MCP server

Universal AI memory layer - cross-client, cross-repo context management with RAG