Memory & Knowledge MCP Servers for DeepSeek Harness

A persistent memory MCP server for AI coding agents — stores, searches, and retrieves atomic learnings per repository.

Intelligent memory API with hybrid caching - Redis for speed, Mem0 for permanence (by n3wth)

Semantic document memory using Redis vector store. Save and recall files with natural language.

Neo4j-based knowledge graph with temporal versioning and semantic search.

MCP server for enabling RAG

MCP server proxying Ratary REST — persistent coding memory for AI assistants

MCP server bridge for RemNote knowledge base

🧠 Self-improving memory system for Claude Code CLI with automatic learning, zero context loss, and advanced analytics

Provides summarised output from various actions that could otherwise eat up tokens and cause crashes

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

Local decisions, evidence, outcomes and reviewed lessons with bounded retrieval and an HTML viewer.

Local-first memory layer for AI agents and humans

Persistent understanding via workflow prompts, typed updates, graph-native code, and supersession.

Persistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys.

Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.

Your agent already broke this three times. ChangeBook tells it before the fourth.

Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.

Token-efficient MCP memory for Markdown vaults. Tiered search, GraphRAG, AI memories.

Content-addressed semantics: fail-closed handshakes over 606 cognitive patterns.

MCP server for Obsidian Smart Connections. Semantic search using your vault's embeddings.

Local-first memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search, GDPR, no cloud.